{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/vision-transformer/papers/11","list_of":"/method/vision-transformer","method":"Vision Transformer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":11,"pages_in_order":22,"rows_per_page":100,"rows":[1001,1100],"of":2144,"counts":{"archive_papers_tagged":2144,"with_a_code_link":1051,"where_syntology_ran_a_sample":328,"not_listed_spam_title":0,"listed":2144,"listed_where_code_ran":328,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":286,"every_run_a_failure_of_syntologys_instrument":42,"listed_with_a_run_with_no_instrument_failure":286,"listed_every_run_a_failure_of_syntologys_instrument":42,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/vision-transformer","prev":"/method/vision-transformer/papers/10","next":"/method/vision-transformer/papers/12","papers":[{"paper":"/paper/idpl-pfod2-a-new-large-scale-dataset-for","slug":"idpl-pfod2-a-new-large-scale-dataset-for","title":"IDPL-PFOD2: A New Large-Scale Dataset for Printed Farsi Optical Character Recognition","date":"2023-12-02","arxiv_id":"2312.01177","n_code_links":1,"syntology":null},{"paper":"/paper/usat-a-unified-self-supervised-encoder-for","slug":"usat-a-unified-self-supervised-encoder-for","title":"USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery","date":"2023-12-02","arxiv_id":"2312.02199","n_code_links":1,"syntology":null},{"paper":"/paper/bcn-batch-channel-normalization-for-image","slug":"bcn-batch-channel-normalization-for-image","title":"BCN: Batch Channel Normalization for Image Classification","date":"2023-12-01","arxiv_id":"2312.00596","n_code_links":1,"syntology":null},{"paper":"/paper/deep-unlearning-fast-and-efficient-training","slug":"deep-unlearning-fast-and-efficient-training","title":"Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting","date":"2023-12-01","arxiv_id":"2312.00761","n_code_links":1,"syntology":{"ran":10,"of":17,"n_ran_checked":10,"n_instrument":0,"unverified":7,"pointer_only":17,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["sangamesh-kodge/class_forgetting"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/gift-generative-interpretable-fine-tuning","slug":"gift-generative-interpretable-fine-tuning","title":"Generative Parameter-Efficient Fine-Tuning","date":"2023-12-01","arxiv_id":"2312.00700","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["savadikarc/gift"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improve-supervised-representation-learning","title":"Improve Supervised Representation Learning with Masked Image Modeling","date":"2023-12-01","arxiv_id":"2312.00950","n_code_links":0,"syntology":null},{"paper":"/paper/synfundus-generating-a-synthetic-fundus","slug":"synfundus-generating-a-synthetic-fundus","title":"SynFundus-1M: A High-quality Million-scale Synthetic fundus images Dataset with Fifteen Types of Annotation","date":"2023-12-01","arxiv_id":"2312.00377","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-lightweight-clustering-framework-for","title":"A Lightweight Clustering Framework for Unsupervised Semantic Segmentation","date":"2023-11-30","arxiv_id":"2311.18628","n_code_links":0,"syntology":null},{"paper":null,"slug":"hifi-tuner-high-fidelity-subject-driven-fine","title":"HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models","date":"2023-11-30","arxiv_id":"2312.00079","n_code_links":0,"syntology":null},{"paper":"/paper/label-efficient-training-of-small-task","slug":"label-efficient-training-of-small-task","title":"Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models","date":"2023-11-30","arxiv_id":"2311.18237","n_code_links":1,"syntology":null},{"paper":null,"slug":"stochastic-vision-transformers-with","title":"Stochastic Vision Transformers with Wasserstein Distance-Aware Attention","date":"2023-11-30","arxiv_id":"2311.18645","n_code_links":0,"syntology":null},{"paper":"/paper/betrayed-by-attention-a-simple-yet-effective","slug":"betrayed-by-attention-a-simple-yet-effective","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","date":"2023-11-29","arxiv_id":"2311.17893","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":8,"n_instrument":2,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shvdiwnkozbw/ssl-uvos"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/contrastive-vision-language-alignment-makes","slug":"contrastive-vision-language-alignment-makes","title":"Contrastive Vision-Language Alignment Makes Efficient Instruction Learner","date":"2023-11-29","arxiv_id":"2311.17945","n_code_links":1,"syntology":null},{"paper":"/paper/pvit-6d-overclocking-vision-transformers-for","slug":"pvit-6d-overclocking-vision-transformers-for","title":"PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens","date":"2023-11-29","arxiv_id":"2311.17504","n_code_links":1,"syntology":null},{"paper":"/paper/spherical-frustum-sparse-convolution-network","slug":"spherical-frustum-sparse-convolution-network","title":"Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation","date":"2023-11-29","arxiv_id":"2311.17491","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["irmvlab/sfcnet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dyra-dynamic-resolution-adjustment-for-scale","slug":"dyra-dynamic-resolution-adjustment-for-scale","title":"DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors","date":"2023-11-28","arxiv_id":"2311.17098","n_code_links":2,"syntology":null},{"paper":null,"slug":"str-cert-robustness-certification-for-deep","title":"STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers","date":"2023-11-28","arxiv_id":"2401.05338","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-learning-based-jamun-leaf-disease","title":"Machine Learning-Based Jamun Leaf Disease Detection: A Comprehensive Review","date":"2023-11-27","arxiv_id":"2311.15741","n_code_links":0,"syntology":null},{"paper":"/paper/chada-vit-channel-adaptive-attention-for","slug":"chada-vit-channel-adaptive-attention-for","title":"ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images","date":"2023-11-26","arxiv_id":"2311.15264","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nicoboou/chadavit","nicoboou/chada_vit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"spectro-vit-a-vision-transformer-model-for","title":"Spectro-ViT: A Vision Transformer Model for GABA-edited MRS Reconstruction Using Spectrograms","date":"2023-11-26","arxiv_id":"2311.15386","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-range-gesture-recognition-using-an-rgb","title":"Ultra-Range Gesture Recognition using a Web-Camera in Human-Robot Interaction","date":"2023-11-26","arxiv_id":"2311.15361","n_code_links":0,"syntology":null},{"paper":null,"slug":"geovit-a-versatile-vision-transformer","title":"GeoViT: A Versatile Vision Transformer Architecture for Geospatial Image Analysis","date":"2023-11-24","arxiv_id":"2311.14301","n_code_links":0,"syntology":null},{"paper":null,"slug":"tvt-training-free-vision-transformer-search","title":"TVT: Training-Free Vision Transformer Search on Tiny Datasets","date":"2023-11-24","arxiv_id":"2311.14337","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-self-supervised-features-for","slug":"understanding-self-supervised-features-for","title":"Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation","date":"2023-11-24","arxiv_id":"2311.14665","n_code_links":0,"syntology":null},{"paper":null,"slug":"fvit-grasp-grasping-objects-with-using-fast","title":"FViT-Grasp: Grasping Objects With Using Fast Vision Transformers","date":"2023-11-23","arxiv_id":"2311.13986","n_code_links":0,"syntology":null},{"paper":"/paper/hevitpose-high-efficiency-vision-transformer","slug":"hevitpose-high-efficiency-vision-transformer","title":"HEViTPose: High-Efficiency Vision Transformer for Human Pose Estimation","date":"2023-11-22","arxiv_id":"2311.13615","n_code_links":1,"syntology":null},{"paper":"/paper/importance-of-feature-extraction-in-the","slug":"importance-of-feature-extraction-in-the","title":"Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend","date":"2023-11-22","arxiv_id":"2311.13717","n_code_links":2,"syntology":null},{"paper":"/paper/unified-classification-and-rejection-a-one","slug":"unified-classification-and-rejection-a-one","title":"Unified Classification and Rejection: A One-versus-All Framework","date":"2023-11-22","arxiv_id":"2311.13355","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"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","official":{"repos":["zhen-cheng121/cpn_ova_unified"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/white-box-transformers-via-sparse-rate-1","slug":"white-box-transformers-via-sparse-rate-1","title":"White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?","date":"2023-11-22","arxiv_id":"2311.13110","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/hover-unet-accelerating-hovernet-with-unet","slug":"hover-unet-accelerating-hovernet-with-unet","title":"HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillation","date":"2023-11-21","arxiv_id":"2311.12553","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-large-scale-car-parts-lscp-dataset-for","title":"A Large-Scale Car Parts (LSCP) Dataset for Lightweight Fine-Grained Detection","date":"2023-11-20","arxiv_id":"2311.11754","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-structure-and-appearance-in-vit","title":"Disentangling Structure and Appearance in ViT Feature Space","date":"2023-11-20","arxiv_id":"2311.12193","n_code_links":0,"syntology":null},{"paper":"/paper/freekd-knowledge-distillation-via-semantic","slug":"freekd-knowledge-distillation-via-semantic","title":"FreeKD: Knowledge Distillation via Semantic Frequency Prompt","date":"2023-11-20","arxiv_id":"2311.12079","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"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","official":{"repos":["Gumpest/FreeKD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tiny-vbf-resource-efficient-vision","title":"Tiny-VBF: Resource-Efficient Vision Transformer based Lightweight Beamformer for Ultrasound Single-Angle Plane Wave Imaging","date":"2023-11-20","arxiv_id":"2311.12082","n_code_links":0,"syntology":null},{"paper":null,"slug":"shape-sensitive-loss-for-catheter-and","title":"Shape-Sensitive Loss for Catheter and Guidewire Segmentation","date":"2023-11-19","arxiv_id":"2311.11205","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-vit-knowledge-distillation","title":"Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction","date":"2023-11-17","arxiv_id":"2311.10305","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-tokenpose-with-sparsity","title":"Improved TokenPose with Sparsity","date":"2023-11-16","arxiv_id":"2311.09653","n_code_links":0,"syntology":null},{"paper":"/paper/unifiedvisiongpt-streamlining-vision-oriented","slug":"unifiedvisiongpt-streamlining-vision-oriented","title":"UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework","date":"2023-11-16","arxiv_id":"2311.10125","n_code_links":1,"syntology":null},{"paper":"/paper/convnet-vs-transformer-supervised-vs-clip","slug":"convnet-vs-transformer-supervised-vs-clip","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","date":"2023-11-15","arxiv_id":"2311.09215","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"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","official":{"repos":["kirill-vish/beyond-inet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dista-denoising-spiking-transformer-with","title":"DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention","date":"2023-11-15","arxiv_id":"2311.09376","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalizable-imitation-learning-through-pre","title":"Generalizable Imitation Learning Through Pre-Trained Representations","date":"2023-11-15","arxiv_id":"2311.09350","n_code_links":0,"syntology":null},{"paper":null,"slug":"act-vit-a-representationally-robust-attention","title":"SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System","date":"2023-11-14","arxiv_id":"2311.08094","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-channel-prototype-network-for-few-shot","title":"Dual-channel Prototype Network for few-shot Classification of Pathological Images","date":"2023-11-14","arxiv_id":"2311.07871","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsvit-a-time-series-vision-transformer-for","title":"TSViT: A Time Series Vision Transformer for Fault Diagnosis","date":"2023-11-12","arxiv_id":"2311.06916","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-stream-scene-understanding-on-graph","title":"Two Stream Scene Understanding on Graph Embedding","date":"2023-11-12","arxiv_id":"2311.06746","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-report-generation-for","slug":"automatic-report-generation-for","title":"Automatic Report Generation for Histopathology images using pre-trained Vision Transformers","date":"2023-11-10","arxiv_id":"2311.06176","n_code_links":1,"syntology":null},{"paper":"/paper/glioblastoma-tumor-segmentation-using-an","slug":"glioblastoma-tumor-segmentation-using-an","title":"Glioblastoma Tumor Segmentation using an Ensemble of Vision Transformers","date":"2023-11-09","arxiv_id":"2312.11467","n_code_links":1,"syntology":null},{"paper":null,"slug":"intelligent-cervical-spine-fracture-detection","title":"Intelligent Cervical Spine Fracture Detection Using Deep Learning Methods","date":"2023-11-09","arxiv_id":"2311.05708","n_code_links":0,"syntology":null},{"paper":"/paper/vision-encoder-decoder-models-for-ai-coaching","slug":"vision-encoder-decoder-models-for-ai-coaching","title":"Vision Encoder-Decoder Models for AI Coaching","date":"2023-11-09","arxiv_id":"2311.16161","n_code_links":2,"syntology":null},{"paper":"/paper/beyond-size-how-gradients-shape-pruning","slug":"beyond-size-how-gradients-shape-pruning","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","date":"2023-11-08","arxiv_id":"2311.04902","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["rocktimjyotidas/gblm-pruner","vila-lab/gblm-pruner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/fibrovit-vision-transformer-based-framework","slug":"fibrovit-vision-transformer-based-framework","title":"FibroVit—Vision transformer-based framework for detection and classification of pulmonary fibrosis from chest CT images","date":"2023-11-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dual-stream-attention-transformers-for-sewer","slug":"dual-stream-attention-transformers-for-sewer","title":"Dual-Stream Attention Transformers for Sewer Defect Classification","date":"2023-11-07","arxiv_id":"2311.16145","n_code_links":1,"syntology":null},{"paper":null,"slug":"fusionvit-hierarchical-3d-object-detection","title":"FusionViT: Hierarchical 3D Object Detection via LiDAR-Camera Vision Transformer Fusion","date":"2023-11-07","arxiv_id":"2311.03620","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-portrait-matting-via-regional","title":"Lightweight Portrait Matting via Regional Attention and Refinement","date":"2023-11-07","arxiv_id":"2311.03770","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-recent-survey-of-the-advancements-in-deep","title":"A Recent Survey of the Advancements in Deep Learning Techniques for Monkeypox Disease Detection","date":"2023-11-06","arxiv_id":"2311.10754","n_code_links":0,"syntology":null},{"paper":"/paper/asymmetric-masked-distillation-for-pre","slug":"asymmetric-masked-distillation-for-pre","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","date":"2023-11-06","arxiv_id":"2311.03149","n_code_links":0,"syntology":null},{"paper":"/paper/cal-detr-calibrated-detection-transformer-1","slug":"cal-detr-calibrated-detection-transformer-1","title":"Cal-DETR: Calibrated Detection Transformer","date":"2023-11-06","arxiv_id":"2311.03570","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["akhtarvision/cal-detr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"machine-learning-based-tea-leaf-disease","title":"Machine Learning-Based Tea Leaf Disease Detection: A Comprehensive Review","date":"2023-11-06","arxiv_id":"2311.03240","n_code_links":0,"syntology":null},{"paper":"/paper/masking-hyperspectral-imaging-data-with","slug":"masking-hyperspectral-imaging-data-with","title":"Masking Hyperspectral Imaging Data with Pretrained Models","date":"2023-11-06","arxiv_id":"2311.03053","n_code_links":1,"syntology":null},{"paper":null,"slug":"sugarvit-multi-objective-regression-of-uav","title":"SugarViT -- Multi-objective Regression of UAV Images with Vision Transformers and Deep Label Distribution Learning Demonstrated on Disease Severity Prediction in Sugar Beet","date":"2023-11-06","arxiv_id":"2311.03076","n_code_links":0,"syntology":null},{"paper":"/paper/rotation-invariant-transformer-for-1","slug":"rotation-invariant-transformer-for-1","title":"Rotation Invariant Transformer for Recognizing Object in UAVs","date":"2023-11-05","arxiv_id":"2311.02559","n_code_links":3,"syntology":null},{"paper":null,"slug":"pros-facial-omni-representation-learning-via","title":"ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation","date":"2023-11-03","arxiv_id":"2311.01929","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-knowledge-from-cnn-transformer","title":"Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition","date":"2023-11-02","arxiv_id":"2311.01283","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-vision-transformer-for-accurate","title":"Efficient Vision Transformer for Accurate Traffic Sign Detection","date":"2023-11-02","arxiv_id":"2311.01429","n_code_links":0,"syntology":null},{"paper":null,"slug":"scattering-vision-transformer-spectral-mixing","title":"Scattering Vision Transformer: Spectral Mixing Matters","date":"2023-11-02","arxiv_id":"2311.01310","n_code_links":0,"syntology":null},{"paper":null,"slug":"patch-based-deep-unsupervised-image","title":"Patch-Based Deep Unsupervised Image Segmentation using Graph Cuts","date":"2023-11-01","arxiv_id":"2311.01475","n_code_links":0,"syntology":null},{"paper":null,"slug":"addressing-limitations-of-state-aware","title":"Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving","date":"2023-10-31","arxiv_id":"2310.20650","n_code_links":0,"syntology":null},{"paper":"/paper/in-search-of-lost-online-test-time-adaptation","slug":"in-search-of-lost-online-test-time-adaptation","title":"In Search of Lost Online Test-time Adaptation: A Survey","date":"2023-10-31","arxiv_id":"2310.20199","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":9,"n_instrument":5,"unverified":3,"pointer_only":7,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jo-wang/otta_vit_survey"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploiting-image-related-inductive-biases-in","slug":"exploiting-image-related-inductive-biases-in","title":"AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking","date":"2023-10-30","arxiv_id":"2310.19542","n_code_links":1,"syntology":null},{"paper":"/paper/mist-medical-image-segmentation-transformer","slug":"mist-medical-image-segmentation-transformer","title":"MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder","date":"2023-10-30","arxiv_id":"2310.19898","n_code_links":1,"syntology":null},{"paper":"/paper/promise-prompt-driven-3d-medical-image","slug":"promise-prompt-driven-3d-medical-image","title":"Promise:Prompt-driven 3D Medical Image Segmentation Using Pretrained Image Foundation Models","date":"2023-10-30","arxiv_id":"2310.19721","n_code_links":1,"syntology":null},{"paper":"/paper/uncovering-prototypical-knowledge-for-weakly","slug":"uncovering-prototypical-knowledge-for-weakly","title":"Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation","date":"2023-10-29","arxiv_id":"2310.19001","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":6,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/local-global-self-supervised-visual","slug":"local-global-self-supervised-visual","title":"Patch-Wise Self-Supervised Visual Representation Learning: A Fine-Grained Approach","date":"2023-10-28","arxiv_id":"2310.18651","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-self-supervised-approach-to-land-cover","title":"A Self-Supervised Approach to Land Cover Segmentation","date":"2023-10-27","arxiv_id":"2310.18251","n_code_links":0,"syntology":null},{"paper":"/paper/qilin-med-vl-towards-chinese-large-vision","slug":"qilin-med-vl-towards-chinese-large-vision","title":"Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare","date":"2023-10-27","arxiv_id":"2310.17956","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["williamliujl/qilin-med-vl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-no-reference-quality-assessment-method-for","title":"A No-Reference Quality Assessment Method for Digital Human Head","date":"2023-10-25","arxiv_id":"2310.16732","n_code_links":0,"syntology":null},{"paper":"/paper/llm-fp4-4-bit-floating-point-quantized","slug":"llm-fp4-4-bit-floating-point-quantized","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","date":"2023-10-25","arxiv_id":"2310.16836","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 3 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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["nbasyl/llm-fp4"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"samclr-contrastive-pre-training-on-complex","title":"SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling","date":"2023-10-23","arxiv_id":"2310.14736","n_code_links":0,"syntology":null},{"paper":"/paper/cxr-llava-multimodal-large-language-model-for","slug":"cxr-llava-multimodal-large-language-model-for","title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","date":"2023-10-22","arxiv_id":"2310.18341","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"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) · 1 unverified","official":{"repos":["ecofri/cxr_llava"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"concept-based-anomaly-detection-in-retail","title":"Concept-based Anomaly Detection in Retail Stores for Automatic Correction using Mobile Robots","date":"2023-10-21","arxiv_id":"2310.14063","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-driving-behavior-for-autonomous","title":"Exploring Driving Behavior for Autonomous Vehicles Based on Gramian Angular Field Vision Transformer","date":"2023-10-21","arxiv_id":"2310.13906","n_code_links":0,"syntology":null},{"paper":null,"slug":"heart-disease-detection-using-vision-based","title":"Heart Disease Detection using Vision-Based Transformer Models from ECG Images","date":"2023-10-19","arxiv_id":"2310.12630","n_code_links":0,"syntology":null},{"paper":"/paper/letfuser-light-weight-end-to-end-transformer","slug":"letfuser-light-weight-end-to-end-transformer","title":"LeTFuser: Light-weight End-to-end Transformer-Based Sensor Fusion for Autonomous Driving with Multi-Task Learning","date":"2023-10-19","arxiv_id":"2310.13135","n_code_links":1,"syntology":null},{"paper":"/paper/minimalist-and-high-performance-semantic","slug":"minimalist-and-high-performance-semantic","title":"Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers","date":"2023-10-19","arxiv_id":"2310.12755","n_code_links":1,"syntology":null},{"paper":null,"slug":"fixpix-fixing-bad-pixels-using-deep-learning","title":"FixPix: Fixing Bad Pixels using Deep Learning","date":"2023-10-18","arxiv_id":"2310.11637","n_code_links":0,"syntology":null},{"paper":null,"slug":"tailoring-adversarial-attacks-on-deep-neural","title":"Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm","date":"2023-10-18","arxiv_id":"2310.13019","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-augmentation-with-controlled-diffusion","title":"Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation","date":"2023-10-15","arxiv_id":"2310.09760","n_code_links":0,"syntology":null},{"paper":"/paper/moemo-vision-transformer-integrating-cross","slug":"moemo-vision-transformer-integrating-cross","title":"MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection","date":"2023-10-15","arxiv_id":"2310.09757","n_code_links":1,"syntology":null},{"paper":null,"slug":"top-k-pooling-with-patch-contrastive-learning","title":"Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation","date":"2023-10-15","arxiv_id":"2310.09828","n_code_links":0,"syntology":null},{"paper":"/paper/faster-3d-cardiac-ct-segmentation-with-vision","slug":"faster-3d-cardiac-ct-segmentation-with-vision","title":"Vision Transformers increase efficiency of 3D cardiac CT multi-label segmentation","date":"2023-10-13","arxiv_id":"2310.09099","n_code_links":1,"syntology":null},{"paper":"/paper/from-clip-to-dino-visual-encoders-shout-in","slug":"from-clip-to-dino-visual-encoders-shout-in","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","date":"2023-10-13","arxiv_id":"2310.08825","n_code_links":1,"syntology":null},{"paper":"/paper/pali-3-vision-language-models-smaller-faster","slug":"pali-3-vision-language-models-smaller-faster","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","date":"2023-10-13","arxiv_id":"2310.09199","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"distilling-efficient-vision-transformers-from","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","date":"2023-10-11","arxiv_id":"2310.07265","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-resistance-to-style-transfer-equal-shape","title":"Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configuration","date":"2023-10-11","arxiv_id":"2310.07555","n_code_links":0,"syntology":null},{"paper":null,"slug":"protohpe-prototype-guided-high-frequency","title":"ProtoHPE: Prototype-guided High-frequency Patch Enhancement for Visible-Infrared Person Re-identification","date":"2023-10-11","arxiv_id":"2310.07552","n_code_links":0,"syntology":null},{"paper":"/paper/ptychodv-vision-transformer-based-deep","slug":"ptychodv-vision-transformer-based-deep","title":"PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction","date":"2023-10-11","arxiv_id":"2310.07504","n_code_links":1,"syntology":null},{"paper":null,"slug":"computational-pathology-at-health-system","title":"Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Images","date":"2023-10-10","arxiv_id":"2310.07033","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-adaptation-of-large-vision-1","slug":"efficient-adaptation-of-large-vision-1","title":"Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing","date":"2023-10-10","arxiv_id":"2310.06234","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["davidyanande/arc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/evit-an-eagle-vision-transformer-with-bi","slug":"evit-an-eagle-vision-transformer-with-bi","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","date":"2023-10-10","arxiv_id":"2310.06629","n_code_links":1,"syntology":null},{"paper":"/paper/learning-stackable-and-skippable-lego-bricks","slug":"learning-stackable-and-skippable-lego-bricks","title":"Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling","date":"2023-10-10","arxiv_id":"2310.06389","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":8,"n_instrument":5,"unverified":4,"pointer_only":8,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["JegZheng/LEGODiffusion"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}}],"record_sha256":"aff03f2c5b1c59423b3cdd515c8bd550f6afcbb7617f2ad47ebe7455b19940e8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}