Browse State-of-the-Art › Image Classification

Image Classification

4,702 papers with code · 166 benchmarks · 283 datasets archive 2025-07-28

AdversarialComputer Vision

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

177 leaderboard tables shown for this task, 166 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 177 until expanded.

Syntology 136 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): ImageNet (11 judged, 0 placed), CIFAR-10 (71 judged, 0 placed), CIFAR-100 (48 judged, 0 placed), ObjectNet (2 judged, 0 placed), MNIST (40 judged, 1 placed), Flowers-102 (9 judged, 0 placed), Fashion-MNIST (11 judged, 0 placed), ImageNet V2 (1 judged, 0 placed), Kuzushiji-MNIST (1 judged, 0 placed), iNaturalist 2019 (1 judged, 0 placed), RESISC45 (2 judged, 0 placed), EuroSAT (10 judged, 0 placed), DTD (7 judged, 1 placed), Food-101 (3 judged, 0 placed), Oxford-IIIT Pets (1 judged, 0 placed), ISIC2018 (1 judged, 0 placed), CelebA 64x64 (1 judged, 0 placed), Imagenette (1 judged, 0 placed), PlantVillage (2 judged, 0 placed), FEMNIST (1 judged, 0 placed), and 3 more leaderboards in the JSON twin. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
ImageNet (1,060 rows) CoCa (finetuned) CoCa: Contrastive Captioners are Image-Text Foundation Models code Syntology 10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified Compare
CIFAR-10 (265 rows) ViT-H/14 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale code Syntology official: harvested, nothing ran · 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified Compare
CIFAR-100 (211 rows) EffNet-L2 (SAM) Sharpness-Aware Minimization for Efficiently Improving Generalization code Syntology official (archive's flag): 7 ran · 15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified Compare
STL-10 (117 rows) µ2Net+ (ViT-L/16) A Continual Development Methodology for Large-scale Multitask... code — Compare
ObjectNet (106 rows) CoCa CoCa: Contrastive Captioners are Image-Text Foundation Models code Syntology 10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified Compare
MNIST (81 rows) Branching/Merging CNN + Homogeneous Vector Capsules No Routing Needed Between Capsules code — Compare
SVHN (62 rows) E2E-M3 Rethinking Recurrent Neural Networks and Other Improvements for... code — Compare
iNaturalist 2018 (60 rows) OmniVec2 OmniVec2 - A Novel Transformer based Network for Large Scale... — — Compare
ImageNet ReaL (57 rows) Baseline (ViT-G/14) Model soups: averaging weights of multiple fine-tuned models... code Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified Compare
Flowers-102 (52 rows) CCT-14/7x2 Escaping the Big Data Paradigm with Compact Transformers code Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified Compare
Clothing1M (51 rows) LRA-diffusion (CC) Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels code Syntology official (archive's flag): 7 ran · 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
mini WebVision 1.0 (47 rows) LRA-diffusion (CLIP ViT) Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels code Syntology official (archive's flag): 7 ran · 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
Fashion-MNIST (34 rows) PreAct-ResNet18 + FMix FMix: Enhancing Mixed Sample Data Augmentation code Syntology official (archive's flag): 5 ran · 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified Compare
VTAB-1k (34 rows) ALIGN (50 hypers/task) Scaling Up Visual and Vision-Language Representation Learning With... code Syntology 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
ImageNet V2 (33 rows) Model soups (BASIC-L) Model soups: averaging weights of multiple fine-tuned models... code Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified Compare
Kuzushiji-MNIST (26 rows) KMNIST-Tiny Efficient Global Neural Architecture Search code — Compare
Stanford Cars (24 rows) efficient adaptive ensembling Efficient Adaptive Ensembling for Image Classification — — Compare
Tiny ImageNet Classification (23 rows) Astroformer Astroformer: More Data Might not be all you need for Classification code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
iNaturalist 2019 (22 rows) Hiera-H (448px) Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
OmniBenchmark (22 rows) NOAH-ViTB/16 Neural Prompt Search code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified Compare
EMNIST-Balanced (20 rows) EMNIST-mobile Efficient Global Neural Architecture Search code — Compare
RESISC45 (20 rows) ResNet50 In-domain representation learning for remote sensing code — Compare
DF20 (19 rows) ViT-Large/16 (384) Danish Fungi 2020 -- Not Just Another Image Recognition Dataset code — Compare
DF20 - Mini (19 rows) ViT-Large/16 (384) Danish Fungi 2020 -- Not Just Another Image Recognition Dataset code — Compare
iNaturalist (19 rows) AIMv2-3B (448 res) Multimodal Autoregressive Pre-training of Large Vision Encoders code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
ColonINST-v1 (Seen) (17 rows) ColonGPT (w/ LoRA, w/o extra data) Frontiers in Intelligent Colonoscopy code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
ColonINST-v1 (Unseen) (17 rows) ColonGPT (w/ LoRA, w/o extra data) Frontiers in Intelligent Colonoscopy code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
WebVision-1000 (16 rows) MAM (ViT-B/16) Improving Image Recognition by Retrieving from Web-Scale Image-Text Data — — Compare
EuroSAT (15 rows) DeepEnsembling Deep Ensembling of Multiband Images for Earth Remote Sensing and... code — Compare
Places205 (15 rows) InternImage-H InternImage: Exploring Large-Scale Vision Foundation Models with... code Syntology official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified Compare
DTD (11 rows) Linear FT(ViT-L/14) Task Arithmetic in the Tangent Space: Improved Editing of... code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
EMNIST-Letters (11 rows) WaveMixLite-112/16 WaveMix: A Resource-efficient Neural Network for Image Analysis code — Compare
Food-101 (11 rows) Bamboo (ViTB/16) Bamboo: Building Mega-Scale Vision Dataset Continually with... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
TCMP-300 (11 rows) Swin-Base — — — Compare
CINIC-10 (9 rows) VIT-L/16 (Spinal FC, Background) Reduction of Class Activation Uncertainty with Background Information code — Compare
Clothing1M (using clean data) (9 rows) CurriculumNet CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images code — Compare
GasHisSDB (8 rows) CoAtNet-1 CoAtNet: Marrying Convolution and Attention for All Data Sizes code Syntology 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified Compare
EMNIST-Digits (7 rows) WaveMixLite-112/16 WaveMix: A Resource-efficient Neural Network for Image Analysis code — Compare
Places365 (7 rows) OmniVec2 OmniVec2 - A Novel Transformer based Network for Large Scale... — — Compare
smallNORB (7 rows) Heinsen Routing An Algorithm for Routing Capsules in All Domains code — Compare
Tiered ImageNet 5-way (5-shot) (7 rows) EGNN+Transduction Edge-labeling Graph Neural Network for Few-shot Learning code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Colored-MNIST(with spurious correlation) (6 rows) MLP-DecAug DecAug: Out-of-Distribution Generalization via Decomposed Feature... code — Compare
iWildCam2020-WILDS (6 rows) COSMO Reviving the Context: Camera Trap Species Classification as Link... code — Compare
Oxford-IIIT Pets (6 rows) CeiT-S (384 finetune resolution) Incorporating Convolution Designs into Visual Transformers code Syntology official (archive's flag): 5 ran · 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result Compare
Caltech-256 (5 rows) AG-Net Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep... code — Compare
Oxford-IIIT Pet Dataset (5 rows) TWIST (ResNet-50) Self-Supervised Learning by Estimating Twin Class Distributions code Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified Compare
Red MiniImageNet 20% label noise (5 rows) NCR (ResNet-18) Learning with Neighbor Consistency for Noisy Labels code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified Compare
Red MiniImageNet 40% label noise (5 rows) NCR (ResNet-18) Learning with Neighbor Consistency for Noisy Labels code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified Compare
Red MiniImageNet 80% label noise (5 rows) NCR (ResNet-18) Learning with Neighbor Consistency for Noisy Labels code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified Compare
CIFAR-10 (with noisy labels) (4 rows) SSR SSR: An Efficient and Robust Framework for Learning with Unknown... code — Compare
CUB (4 rows) Entropy-based Logic Explained Network Entropy-based Logic Explanations of Neural Networks code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Food-101N (4 rows) LRA-diffusion (CLIP ViT) Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels code Syntology official (archive's flag): 7 ran · 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
ISIC2018 (4 rows) UniNet UniNet: A Contrastive Learning-guided Unified Framework with... code — Compare
JFT-300M (4 rows) V-MoE-H/14 (Every-2) Scaling Vision with Sparse Mixture of Experts code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
MAMe (4 rows) EfficientNet-B3 The MAMe Dataset: On the relevance of High Resolution and Variable... code — Compare
N-MNIST (4 rows) STS-ResNet Convolutional Spiking Neural Networks for Spatio-Temporal Feature... code — Compare
ObjectNet (Bounding Box) (4 rows) BiT-L (ResNet) Big Transfer (BiT): General Visual Representation Learning code Syntology community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
Oracle-MNIST (4 rows) ResNet-18 + Vision Eagle Attention Vision Eagle Attention: a new lens for advancing image classification code — Compare
Places365-Standard (4 rows) SWAG (ViT H/14) Revisiting Weakly Supervised Pre-Training of Visual Perception Models code — Compare
Red MiniImageNet 60% label noise (4 rows) InstanceGM-SS Instance-Dependent Noisy Label Learning via Graphical Modelling code — Compare
Tiny-ImageNet (4 rows) UPANets UPANets: Learning from the Universal Pixel Attention Networks code — Compare
Visual Wake Words (4 rows) HyT-NAS-BA HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices — — Compare
BreakHis (3 rows) WaveMix Which Backbone to Use: A Resource-efficient Domain Specific... code — Compare
CelebA 64x64 (3 rows) cFlow Null-sampling for Interpretable and Fair Representations code — Compare
EarlyNSD (3 rows) DenseNet121_256x256_Nutrispace Nutrispace: A novel color space to enhance deep learning based... — — Compare
EuroSAT-SAR (3 rows) FG-MAE (ViT-S/16) Feature Guided Masked Autoencoder for Self-supervised Learning in... code — Compare
FlickrLogos-32 (3 rows) TC-VII (with outside data) Deep Learning for Logo Recognition — — Compare
Id Pattern Dataset (3 rows) Claude 3 Opus Identification of Stone Deterioration Patterns with Large Multimodal Models code — Compare
Kvasir (3 rows) HiFuse_Small HiFuse: Hierarchical Multi-Scale Feature Fusion Network for... code — Compare
Malaria Dataset (3 rows) kEffNet-B0 V2 16ch An Enhanced Scheme for Reducing the Complexity of Pointwise... code — Compare
N-Caltech 101 (3 rows) mMND (STDP) Sequence Approximation using Feedforward Spiking Neural Network... — — Compare
SIPaKMeD (3 rows) DL+PCA+GWO Cervical Cytology Classification Using PCA & GWO Enhanced Deep... code — Compare
Causal3DIdent (2 rows) SimCLR Self-Supervised Learning with Data Augmentations Provably Isolates... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
Certificate Verification (2 rows) ResMLP-24 ResMLP: Feedforward networks for image classification with... code Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
CIFAR-10 (40 Labels, ImageNet-100 Unlabeled) (2 rows) UnMixMatch Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data code — Compare
CIFAR-10, 40% Symmetric Noise (2 rows) FaMUS Faster Meta Update Strategy for Noise-Robust Deep Learning code Syntology official (archive's flag): 2 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified Compare
CIFAR-10, 60% Symmetric Noise (2 rows) MentorMix Faster Meta Update Strategy for Noise-Robust Deep Learning code Syntology official (archive's flag): 2 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified Compare
CIFAR-10 Image Classification (2 rows) ASF-former-S Adaptive Split-Fusion Transformer code — Compare
CIFAR-100, 40% Symmetric Noise (2 rows) FaMUS Faster Meta Update Strategy for Noise-Robust Deep Learning code Syntology official (archive's flag): 2 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified Compare
CLEVR/Count (2 rows) SEER (RegNet10B) Vision Models Are More Robust And Fair When Pretrained On... code — Compare
CLEVR/Dist (2 rows) SEER (RegNet10B) Vision Models Are More Robust And Fair When Pretrained On... code — Compare
CUB-200-2011 (2 rows) Sparse-CBM Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning code — Compare
Fracture/Normal Shoulder Bone X-ray Images on MURA (2 rows) Our Ensemble Learning-2 Classification of Shoulder X-Ray Images with Deep Learning Ensemble Models — — Compare
Galaxy10 DECals (2 rows) WaveMix WaveMix: A Resource-efficient Neural Network for Image Analysis code — Compare
Gaze-CIFAR-10 (2 rows) DSGE-ConvNeXtV2 Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification code — Compare
HErlev (2 rows) Fuzzy Distance Ensemble A fuzzy distance-based ensemble of deep models for cervical cancer... code — Compare
ImageNet-10 (2 rows) ResNet-50 + UDA+AutoDropout AutoDropout: Learning Dropout Patterns to Regularize Deep Networks code — Compare
ImageNet-100 (TEMI Split) (2 rows) SparseSwin with L2 SparseSwin: Swin Transformer with Sparse Transformer Block code — Compare
ImageNet-Hard (2 rows) EfficientNet-L2-Ns — — — Compare
Imagenette (2 rows) µ2Net+ (ViT-L/16) A Continual Development Methodology for Large-scale Multitask... code — Compare
Imbalanced CUB-200-2011 (2 rows) Multi-task A New Periocular Dataset Collected by Mobile Devices in... — — Compare
Intel Image Classification (2 rows) ResNet-18 + Vision Eagle Attention Vision Eagle Attention: a new lens for advancing image classification code — Compare
ISIC 2018 (2 rows) HiFuse_Base HiFuse: Hierarchical Multi-Scale Feature Fusion Network for... code — Compare
Large Labelled Logo Dataset (L3D) (2 rows) L3D_original_2level The Large Labelled Logo Dataset (L3D): A Multipurpose and... code — Compare
LIMUC (2 rows) Inception-v3 Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified Compare
Noisy MNIST (AWGN) (2 rows) PCGAN-CHAR PCGAN-CHAR: Progressively Trained Classifier Generative... — — Compare
Noisy MNIST (Contrast) (2 rows) PCGAN-CHAR PCGAN-CHAR: Progressively Trained Classifier Generative... — — Compare
Noisy MNIST (Motion) (2 rows) PCGAN-CHAR PCGAN-CHAR: Progressively Trained Classifier Generative... — — Compare
ObjectNet (ImageNet classes) (2 rows) Diffusion Classifier (zero-shot) Your Diffusion Model is Secretly a Zero-Shot Classifier code Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
PlantDoc (2 rows) SCOLD A Vision-Language Foundation Model for Leaf Disease Identification code — Compare
PlantVillage (2 rows) adaptive minimal ensembling Improving plant disease classification by adaptive minimal ensembling — — Compare
split CIFAR-100 (2 rows) OFSCIL 12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning code — Compare
WebVision (2 rows) PropMix (Ours) PropMix: Hard Sample Filtering and Proportional MixUp for Learning... code — Compare
AIDER (1 row) TakuNet FP=16 TakuNet: an Energy-Efficient CNN for Real-Time Inference on... code — Compare
AIDERV2 (1 row) TakuNet FP=16 TakuNet: an Energy-Efficient CNN for Real-Time Inference on... code — Compare
AmsterTime (1 row) AP-GeM (ResNet-101) AmsterTime: A Visual Place Recognition Benchmark Dataset for... code — Compare
ArtDL (1 row) ResNet-50 A Data Set and a Convolutional Model for Iconography... code — Compare
CARS196 (1 row) µ2Net+ (ViT-L/16) A Continual Development Methodology for Large-scale Multitask... code — Compare
cats_vs_dogs (1 row) µ2Net+ (ViT-L/16) A Continual Development Methodology for Large-scale Multitask... code — Compare
Chaoyang (1 row) HSANR Hard Sample Aware Noise Robust Learning for Histopathology Image... code — Compare
CIFAR-100, 60% Symmetric Noise (1 row) MentorMix Faster Meta Update Strategy for Noise-Robust Deep Learning code Syntology official (archive's flag): 2 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified Compare
CIFAR-100 (alpha=0, 20 clients per round) (1 row) FedAvgM + ASAM + SWA Improving Generalization in Federated Learning by Seeking Flat Minima code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
CIFAR-100C (1 row) Astroformer Astroformer: More Data Might not be all you need for Classification code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
cifar-10,4000 (1 row) WRN-28-2 + UDA+AutoDropout AutoDropout: Learning Dropout Patterns to Regularize Deep Networks code — Compare
cifar10 (1 row) SAM — — — Compare
cifar100 (1 row) shreynet Deep Residual Learning for Image Recognition code Syntology official: no sample here; runs from other or unrecorded repositories · 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified Compare
Deep PCB (1 row) ResNet Improving Model Performance and Removing the Class Imbalance... — — Compare
DVS128 Gesture (1 row) SNN Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking... code — Compare
EMNIST-Byclass (1 row) WaveMixLite-128/7 WaveMix: A Resource-efficient Neural Network for Image Analysis code — Compare
EMNIST-Bymerge (1 row) WaveMixLite-128/16 WaveMix: A Resource-efficient Neural Network for Image Analysis code — Compare
ESC-50 (1 row) SDGM-D Performance of Gaussian Mixture Model Classifiers on Embedded... code — Compare
FEMNIST (1 row) pFedBreD_ns_mg Personalized Federated Learning with Hidden Information on... — — Compare
FGVC Aircraft (1 row) TransBoost-ResNet50 TransBoost: Improving the Best ImageNet Performance using Deep Transduction code — Compare
FGVC-Aircraft (1 row) EnGraf-Net101 (G=4, H=1) EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse... code — Compare
Flower102 (1 row) efficient adaptive ensembling Efficient Adaptive Ensembling for Image Classification — — Compare
Flowers (Tensorflow) (1 row) CNN+ Wilson-Cowan model RNN Learning in Wilson-Cowan model for metapopulation code — Compare
FMD (materials) (1 row) RADAM (ConvNeXt-L) RADAM: Texture Recognition through Randomized Aggregated Encoding... code — Compare
GTSRB (1 row) SAG-ViT SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph... code — Compare
iCassava'19 (1 row) E2E-3M Rethinking Recurrent Neural Networks and Other Improvements for... code — Compare
delete (1 row) (unnamed in the archive) Understanding the Robustness of Randomized Feature Defense Against... code Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified Compare
ImageNet-100 (Class-IL, 5T) (1 row) MoCo + CaSSLe Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
imagenet-1k (1 row) BinaryViT BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models code — Compare
ImageNet-32 (1 row) WRN (N=28, k=10) A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets code — Compare
ImageNet-64 (1 row) WRN (N=36, k=5) A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets code — Compare
ImageNet-9 (1 row) SqueezeNet + Simple Bypass SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and... code Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified Compare
ImageNet-P (1 row) SqueezeNet + Simple Bypass SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and... code Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified Compare
ImageNet-Sketch (1 row) µ2Net+ (ViT-L/16) A Continual Development Methodology for Large-scale Multitask... code — Compare
iNat2021-mini (1 row) WaveMix-256/16 (level 2) WaveMix: A Resource-efficient Neural Network for Image Analysis code — Compare
ISBNet (1 row) ThanosNet ThanosNet: A Novel Trash Classification Method Using Metadata code — Compare
KITTI-Dist (1 row) SEER (RegNet10B) Vision Models Are More Robust And Fair When Pretrained On... code — Compare
KMNIST (1 row) µ2Net (ViT-L/16) An Evolutionary Approach to Dynamic Introduction of Tasks in... code — Compare
KTH-TIPS2 (1 row) RADAM (ConvNeXt-XL) RADAM: Texture Recognition through Randomized Aggregated Encoding... code — Compare
LabelMe (1 row) CoNAL Learning from Crowds by Modeling Common Confusions code — Compare
LeafNet (1 row) SCOLD A Vision-Language Foundation Model for Leaf Disease Identification code — Compare
mnist (1 row) WaveMixLite WaveMix: A Resource-efficient Neural Network for Image Analysis code — Compare
MNIST-rot-12 (1 row) PDO-eConv (ours) PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions code Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified Compare
MNIST-rot-12k (DA) (1 row) PDO-eConv (ours) PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions code Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified Compare
MultiMNIST (1 row) CapsNet Dynamic Routing Between Capsules code Syntology official (archive's flag): 1 ran · 75 ran (of which 0 constructed an object rather than computing a result; 58 with no instrument failure: 0 honoured, 0 violated, 58 with no contract checked; 17 where Syntology's instrument failed) · 43 unverified Compare
NCT-CRC-HE-100K (1 row) SAG-ViT SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph... code — Compare
No Background RGB Arabic Alphabets Sign Language Dataset (1 row) ArabSignNet Deep Learning Recognition for Arabic Alphabet Sign Language RGB Dataset — — Compare
PASCAL VOC 2007 (1 row) NNCLR With a Little Help from My Friends: Nearest-Neighbor Contrastive... code Syntology 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result Compare
Pets SAM (1 row) efficient adaptive ensembling Efficient Adaptive Ensembling for Image Classification — — Compare
PRImA (1 row) ResNet-152 2x (RS training) Revisiting ResNets: Improved Training and Scaling Strategies code — Compare
QMNIST (1 row) Deep regularization Deep regularization and direct training of the inner layers of... code — Compare
RGB Arabic Alphabet Sign Language (AASL) dataset (1 row) ArabSignNet Deep Learning Recognition for Arabic Alphabet Sign Language RGB Dataset — — Compare
SARS-COV-2 (1 row) Fuzzy rank-based fusion of CNN models using Gompertz function Fuzzy Rank-based Fusion of CNN Models using Gompertz Function for... code — Compare
So2Sat LCZ42 (1 row) ResNet50 In-domain representation learning for remote sensing code — Compare
Split CIFAR-10 (1 row) Model with negotiation paradigm Negotiated Representations to Prevent Forgetting in Machine... code — Compare
Split Fashion M-NIST (1 row) Model with negotiation paradigm Negotiated Representations to Prevent Forgetting in Machine... code — Compare
Split M-NIST (1 row) Model with negotiation paradigm Negotiated Representations to Prevent Forgetting in Machine... code — Compare
Sports10 (1 row) Max Margin Contrastive Contrastive Learning of Generalized Game Representations code — Compare
Stanford Online Products (1 row) µ2Net+ (ViT-L/16) A Continual Development Methodology for Large-scale Multitask... code — Compare
SUN397 (1 row) TransBoost-ResNet50 TransBoost: Improving the Best ImageNet Performance using Deep Transduction code — Compare
Surrey ASL (1 row) E2E-3M Rethinking Recurrent Neural Networks and Other Improvements for... code — Compare
Training and validation dataset of capsule vision 2024 challenge. (1 row) BiomedCLIP+PubmedBERT A Multimodal Approach For Endoscopic VCE Image Classification... code — Compare
VizWiz-Classification (1 row) VOLO-D5 VOLO: Vision Outlooker for Visual Recognition code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
chbh7051/vit-base-driver-drowsiness-detection (0 rows) no rows in the archive — —
Custom Dataset (0 rows) no rows in the archive — —
Custom DeepFake Dataset (0 rows) no rows in the archive — —
finetuned-websites (0 rows) no rows in the archive — —
Human_Action_Recognition (0 rows) no rows in the archive — —
image_folder (0 rows) no rows in the archive — —
imagefolder (0 rows) no rows in the archive — —
indian_food_images (0 rows) no rows in the archive — —
mriDataSet (0 rows) no rows in the archive — —
New Plant Diseases Dataset (0 rows) no rows in the archive — —
PCam (0 rows) no rows in the archive — —

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

283 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 283 until expanded.

CIFAR-10ImageNetCIFAR-100MNISTCelebASVHNFashion-MNISTCUB-200-2011Oxford 102 FlowerTiny ImageNetSTL-10DTDFood-101Stanford CarsEuroSATiNaturalistPlaces205FGVC-AircraftBDD100KCaltech-256ESC-50GTSRBtieredImageNetClothing1MImageNet-SketchEMNISTNAS-Bench-201YFCC100MStanford Online ProductsVGG-SoundAI2DVTABCINIC-10RESISC45Extended Yale BWebVisionLabelMeObjectNetfMoWOxford5kMeta-DatasetPASCAL VOC 2007JFT-300MKvasirImageNet-32smallNORBN-Caltech 101PCamStylized ImageNetDVS128 GestureTiny ImagesCIFAR-10NKuzushiji-MNISTOxford-IIIT Pet DatasetImageNet-OAbstractReasoningBigEarthNetChestX-ray8PlantVillageCIFAR-100NPlaces365Oxford-IIIT PetsWOSPGMMINCTiny-ImageNet-CMultiMNISTSUN397CARS196JFT-3BMillion-AIDVisual Wake WordsImagenetteSUN AttributeOpen Images V4ImageNet-64ImageNet-POmniBenchmarkEyeQiNat2021FlickrLogos-32QMNISTUrbanCarsBAM!ELEVATERImageNet-WIP102VizWiz-ClassificationLAGMSegETHOSPlantDocChaoyangDeepFishLaMemMLRSNetFEMNISTFood2KN-MNISTTAU Urban Acoustic Scenes 2019Cats and DogsCausal3DIdentHyper-Kvasir DatasetImageNet-100 (TEMI Split)BCN_20000BCNBBreakHisFoodX-251GasHisSDBSo2Sat LCZ42Kuzushiji-49AmsterTimeiCartoonFaceiWildCam2020-WILDSKMNISTAIDERColonINST-v1ColonINST-v1 (Seen)ColonINST-v1 (Unseen)NCT-CRC-HE-100KArtBench-10 (32x32)BambooBook Cover DatasetDF20DFUC2021Grocery StoreImageNet-9Kannada-MNISTKaoKoreNumtaDBPMDataPS-BattlesSI-SCOREColored-MNIST(with spurious correlation)F-CelebA (10 tasks)Food-101NGalaxy Zoo DECaLSMalaria DatasetOOD-CVOpen Images V7Red MiniImageNet 20% label noiseRed MiniImageNet 40% label noiseRed MiniImageNet 80% label noiseUrban EnvironmentsHErlevImageNet-HardImageNet-PatchInsPLADIntel Image ClassificationMuMiNNIH-CXR-LTRF100Sewer-MLSIPaKMeDSports10Tencent ML-ImagesCI-MNISTDiagSetETHECEuroSAT-SARKTH-TIPS2Kuzushiji-KanjiLIMUCMIMIC-CXR-LTMNIST Large Scale datasetOracle-MNISTWHU-HiACL-FigAnimals-10AtlasDEIC BenchmarkDiffusion DeepfakeDirty-MNISTFireRiskFMD (materials)Image and Video AdvertisementsLKSLSA16OFDIWRGB Arabic Alphabets Sign Language DatasetSIDD-ImageStream-51AdvNetASIRRACARBENCHAMMICross-View Time DatasetDeep PCBDF20 - MiniDIB-10KEndotect Polyp Segmentation Challenge DatasetHiAMLInceptionInVar-100Kvasir-CapsuleMAMeNew Plant Diseases DatasetPolSFS2RDASI-ScoreSTIRTwo-PathUltra Fine-Grained Leaves (Cotton, SoyAgeing, SoyGene, SoyGlobal, SoyLocal)Vistas-NPAIDERV2AjwaOrMedjoolARC-100ArtDLBanappleBankNote-NetCervix93 Cytology DatasetCleanSTL-10CNFOOD-241CNFOOD-241-ChenCross-View Time Dataset (Cross-Camera Split)Cultural Events Classification using Hyper-parameter Optimization of Deep Learning TechniqueDalleStreetDry Bean DatasetEarlyNSDENSegFathomNet2023Fruits Dataset for ClassificationGaze-CIFAR-10HaSPeRIcon645Id Pattern DatasetidspritesImageNet 50 samples per classIMPACT PatentiNaturalist Fine-Grained GeolocationIndian Party Symbol DatasetIran's Built Heritage Binary Image Classification DatasetIRMAISBNetJAMBOLabelsLAOFIW DatasetLarge Labelled Logo Dataset (L3D)LeafNetMapReader DataMuMiN-largeMuMiN-mediumMuMiN-smallNo Background RGB Arabic Alphabets Sign Language DatasetNotre-Dame Cathedral FireOLID IOmni-ImageOpenStreetMap Multi-Sensor Scene ClassificationOrchid2024PhotozillaPoTATO: A Dataset for Analyzing Polarimetric Traces of Afloat Trash ObjectsPRImARGB Arabic Alphabet Sign Language (AASL) datasetShipSpottingSolarDKSPOT-10SSBI DatasetSuSy DatasetSVLDSynthetic COVID-19 CXR DatasetTCB-DSTEM nanowire morphologies for classification and segmentationtopex-printerTsinghua DogsTwinSynthsWeapon Detection DatasetYFCC100M Fine-Grained GeolocationADFIAlpaca Dataset Image ClassificationAppleScabFDsAppleScabLDsCCICCEAHB2021-5Corn Kernel Images DatasetCorn Seeds DataseteAppleScabFour ShapesLusitano Fabric Defect Detection DatasetMoroccan Monay datasetMudestredaPortuguese Meals DatasetSakha-TBTCMP-300

Subtasks archive 2025-07-28

33 subtasks in the archive's task tree. 30 shown of 33 until expanded.

Papers archive 2025-07-28

archive papers tagged: 10,488 · with a code link: 4,702 · where Syntology ran a sample: 1,392 (1,143 with a run with no instrument failure, 249 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1,392 of 10,488 tagged: 1,143 with a run with no instrument failure, 249 where every run was a failure of Syntology's instrument)

Page 1 of 105: papers 1 to 100 of 10,488, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 92 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections