Browse State-of-the-Art › Semantic Segmentation

Semantic Segmentation

6,644 papers with code · 150 benchmarks · 347 datasets archive 2025-07-28

Computer CodeComputer VisionMedicalRobots

Benchmarks archive 2025-07-28

151 leaderboard tables shown for this task (1 more in the archive withheld as spam; see /not-shown), 150 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 151 until expanded.

Syntology 35 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; 2 placed): ADE20K (7 judged, 0 placed), Cityscapes val (6 judged, 1 placed), ADE20K val (17 judged, 0 placed), PASCAL Context (2 judged, 1 placed), S3DIS Area5 (2 judged, 0 placed), ScanNet (1 judged, 0 placed), SUN-RGBD (2 judged, 0 placed), BDD100K val (1 judged, 0 placed), LoveDA (2 judged, 0 placed), FMB Dataset (1 judged, 0 placed), GTAV-to-Cityscapes Labels (2 judged, 0 placed), ScanNetV2 (2 judged, 0 placed), Potsdam (1 judged, 0 placed), DDD17 (1 judged, 0 placed), DSEC (3 judged, 0 placed), Kvasir-Instrument (1 judged, 0 placed), HAM10000 (2 judged, 0 placed), MixedWM38 (1 judged, 0 placed). 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
ADE20K (235 rows) ViT-P (InternImage-H) The Missing Point in Vision Transformers for Universal Image Segmentation code — Compare
NYU Depth v2 (121 rows) OmniVec2 OmniVec2 - A Novel Transformer based Network for Large Scale... — — Compare
Cityscapes test (105 rows) VLTSeg Strong but simple: A Baseline for Domain Generalized Dense... code — Compare
Cityscapes val (99 rows) ViT-P (InternImage-H) The Missing Point in Vision Transformers for Universal Image Segmentation code — Compare
ADE20K val (95 rows) BEiT-3 Image as a Foreign Language: BEiT Pretraining for All Vision and... code — Compare
PASCAL Context (66 rows) VPNeXt VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer — — Compare
S3DIS Area5 (61 rows) Sonata + PTv3 Sonata: Self-Supervised Learning of Reliable Point Representations code Syntology official (archive's flag): 11 ran · 11 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; 3 where Syntology's instrument failed) · 8 unverified Compare
S3DIS (54 rows) Sonata + PTv3 Sonata: Self-Supervised Learning of Reliable Point Representations code Syntology official (archive's flag): 11 ran · 11 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; 3 where Syntology's instrument failed) · 8 unverified Compare
PASCAL VOC 2012 test (51 rows) DeepLabv3+ (Xception-65-JFT) Encoder-Decoder with Atrous Separable Convolution for Semantic... code Syntology community repositories only · 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified Compare
ScanNet (45 rows) DITR DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation code — Compare
SUN-RGBD (44 rows) GeminiFusion (Swin-Large) GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer code Syntology official (archive's flag): 7 ran · 7 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; 2 where Syntology's instrument failed) · 3 unverified Compare
DensePASS (36 rows) Trans4PASS+ (multi-scale) Behind Every Domain There is a Shift: Adapting Distortion-aware... code — Compare
PASCAL VOC 2012 val (29 rows) EfficientNet-L2+NAS-FPN (single scale test, with self-training) Rethinking Pre-training and Self-training code — Compare
DADA-seg (28 rows) MMUDA Towards Robust Semantic Segmentation of Accident Scenes via... code — Compare
DeLiVER (26 rows) CAFuser-CAA CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic... 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
Stanford2D3D Panoramic (25 rows) SFSS-MMSI (RGB+HHA) Single Frame Semantic Segmentation Using Multi-Modal Spherical Images code — Compare
BDD100K val (24 rows) VLTSeg Strong but simple: A Baseline for Domain Generalized Dense... code — Compare
MCubeS (22 rows) StitchFusion (RGB-A-D-N) StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal... code — Compare
CamVid (21 rows) SERNet-Former SERNet-Former: Semantic Segmentation by Efficient Residual Network... code — Compare
COCO-Stuff test (21 rows) VPNeXt VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer — — Compare
ImageNet-S (20 rows) TEC (ViT-B/16, 224x224, SSL+FT, mmseg) Towards Sustainable Self-supervised Learning code Syntology official (archive's flag): 6 ran · 6 ran (of which 6 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) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result Compare
ISPRS Potsdam (20 rows) AerialFormer-B AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation code — Compare
LaRS (20 rows) SWIM^2 (Mask2Former) The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 — — Compare
iSAID (19 rows) SegNeXt-L SegNeXt: Rethinking Convolutional Attention Design for Semantic... code — Compare
LoveDA (19 rows) U-Net (MaxViT-S) U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery — — Compare
KITTI-360 (17 rows) DiPFormer Depth Matters: Exploring Deep Interactions of RGB-D for Semantic... — — Compare
Semantic3D (17 rows) Feature Geometric Net FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network... code — Compare
Trans10K (15 rows) Trans4Trans (M) Trans4Trans: Efficient Transformer for Transparent Object... code — Compare
Dark Zurich (14 rows) Refign (HRDA) Refign: Align and Refine for Adaptation of Semantic Segmentation... code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
FMB Dataset (14 rows) RoadFormer+ (RGB-Infrared) RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware... — — Compare
UrbanLF (14 rows) CMNeXt (RGB-LF80) Delivering Arbitrary-Modal Semantic Segmentation code Syntology official (archive's flag): 7 ran · 7 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; 2 where Syntology's instrument failed) · 0 unverified Compare
LIP val (13 rows) Hulk(Finetune, ViT-L) Hulk: A Universal Knowledge Translator for Human-Centric Tasks code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 11 unverified Compare
Nighttime Driving (13 rows) TADP Text-image Alignment for Diffusion-based Perception code — Compare
Vaihingen (13 rows) CMX CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers code Syntology official (archive's flag): 2 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) · 0 unverified Compare
ZJU-RGB-P (13 rows) RoadFormer+ (ConvNeXt-L, RGB-AoLP) RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware... — — Compare
EventScape (12 rows) CMX (B4) CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers code Syntology official (archive's flag): 2 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) · 0 unverified Compare
GTAV-to-Cityscapes Labels (12 rows) MIC MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation code — Compare
ISPRS Vaihingen (12 rows) LSKNet-S LSKNet: A Foundation Lightweight Backbone for Remote Sensing code — Compare
ScanNetV2 (12 rows) CMX CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers code Syntology official (archive's flag): 2 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) · 0 unverified Compare
BJRoad (11 rows) CMNeXt Delivering Arbitrary-Modal Semantic Segmentation code Syntology official (archive's flag): 7 ran · 7 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; 2 where Syntology's instrument failed) · 0 unverified Compare
Potsdam (11 rows) LMFNet-3 LMFNet: An Efficient Multimodal Fusion Approach for Semantic... — — Compare
US3D (11 rows) LMFNet-3 LMFNet: An Efficient Multimodal Fusion Approach for Semantic... — — Compare
Fine-Grained Grass Segmentation Dataset (10 rows) D2LS Dynamic Dictionary Learning for Remote Sensing Image Segmentation code Syntology 9 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; 1 where Syntology's instrument failed) · 3 unverified Compare
SpaceNet 1 (10 rows) MAE+MTP(ViT-L) MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining code Syntology official (archive's flag): 1 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
SYN-UDTIRI (10 rows) RoadFormer+ (B) RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware... — — Compare
UAVid (10 rows) U-Net Ensemble U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery — — Compare
COCO (Common Objects in Context) (9 rows) HyperSeg HyperSeg: Towards Universal Visual Segmentation with Large Language Model code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified Compare
DDD17 (9 rows) BRENet Rethinking RGB-Event Semantic Segmentation with a Novel... code — Compare
DELIVER (9 rows) CAFuser CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic... 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
DSEC (9 rows) BRENet Rethinking RGB-Event Semantic Segmentation with a Novel... code — Compare
INRIA Aerial Image Labeling (8 rows) UANet(PVT-V2-B2) Building Extraction from Remote Sensing Images via an... code — Compare
LLRGBD-synthetic (8 rows) SMMCL (SegNeXt-B) Understanding Dark Scenes by Contrasting Multi-Modal Observations code — Compare
Mapillary val (8 rows) AO-SegNet Interactive Learning of Intrinsic and Extrinsic Properties for... code — Compare
MCubeS (P) (8 rows) MMSFormer (RGB-A-D) MMSFormer: Multimodal Transformer for Material and Semantic Segmentation code — Compare
SpectralWaste (8 rows) CMX (RGB-HYPER) CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers code Syntology official (archive's flag): 2 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) · 0 unverified Compare
UPLight (8 rows) ShareCMP (B2 RGB-FP) ShareCMP: Polarization-Aware RGB-P Semantic Segmentation 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) · 0 unverified Compare
FoodSeg103 (7 rows) FoodSAM FoodSAM: Any Food Segmentation code — Compare
KITTI Semantic Segmentation (7 rows) RPVNet [xu2021rpvnet] Spherical Transformer for LiDAR-based 3D Recognition code Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified Compare
Pothole Mix (7 rows) Baseline - DeepLabv3+ SHREC 2022: pothole and crack detection in the road pavement using... code — Compare
SELMA (7 rows) CMX CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers code Syntology official (archive's flag): 2 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) · 0 unverified Compare
SkyScapes-Dense (7 rows) SkyScapesNet-Dense SkyScapes Fine-Grained Semantic Understanding of Aerial Scenes — — Compare
SYNTHIA-to-Cityscapes (7 rows) HRDA + PiPa PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain... code — Compare
VDD (7 rows) Segformer-B2 VDD: Varied Drone Dataset for Semantic Segmentation code — Compare
ACDC Scribbles (6 rows) ScribFormer ScribFormer: Transformer Makes CNN Work Better for Scribble-based... code — Compare
Event-based Segmentation Dataset (6 rows) Bimodal SegNet Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames... code — Compare
GAMUS (6 rows) TIMF GAMUS: A Geometry-aware Multi-modal Semantic Segmentation... code — Compare
Porto (6 rows) CMNeXt Delivering Arbitrary-Modal Semantic Segmentation code Syntology official (archive's flag): 7 ran · 7 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; 2 where Syntology's instrument failed) · 0 unverified Compare
Stanford2D3D - RGBD (6 rows) CMX (SegFormer-B4) CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers code Syntology official (archive's flag): 2 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) · 0 unverified Compare
SynPASS (6 rows) Trans4PASS+ Behind Every Domain There is a Shift: Adapting Distortion-aware... code — Compare
TLCGIS (6 rows) SA-Gate Bi-directional Cross-Modality Feature Propagation with... code — Compare
FLAIR (French Land cover from Aerospace ImageRy) (5 rows) Ensemble-04 MiT-0 MiT-1 RNX-1 RNX-2 Modernized Training of U-Net for Aerial Semantic Segmentation code — Compare
Hypersim (5 rows) EMSANet (2x ResNet-34 NBt1D) PanopticNDT: Efficient and Robust Panoptic Mapping code Syntology community repositories only · 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) · 7 unverified Compare
RELLIS-3D Dataset (5 rows) Swiftnet Semantic Segmentation with High Inference Speed in Off-Road Environments code — Compare
Replica (5 rows) LabelMaker LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
ShapeNet (5 rows) PatchFormer PatchFormer: An Efficient Point Transformer with Patch Attention — — Compare
Synthetic Bathing Perception (5 rows) CMX-SRA CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers code Syntology official (archive's flag): 2 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) · 0 unverified Compare
Toronto-3D L002 (5 rows) EyeNet Human Vision Based 3D Point Cloud Semantic Segmentation of... code — Compare
BIG (4 rows) PSPNet + CascadePSP CascadePSP: Toward Class-Agnostic and Very High-Resolution... code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified Compare
CC3M-TagMask (4 rows) TTD (TCL) TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in... 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
Fine-Grained Cloud Segmentation Dataset (4 rows) D2LS Dynamic Dictionary Learning for Remote Sensing Image Segmentation code Syntology 9 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; 1 where Syntology's instrument failed) · 3 unverified Compare
Lombardia Sentinel-2 Image Time Series for Crop Mapping (4 rows) UNet3D Enhancing crop segmentation in satellite image time-series with... code — Compare
Matterport3D (4 rows) SFSS-MMSI (RGB+Depth) Single Frame Semantic Segmentation Using Multi-Modal Spherical Images code — Compare
Okutama Drone and Swiss Drone Dataset (4 rows) DeepLabv3+‐ResNet‐101 Deep learning with RGB and thermal images onboard a drone for... — — Compare
PETRAW (4 rows) NCC Next PEg TRAnsfer Workflow recognition challenge report: Does... — — Compare
Structured3D (4 rows) SFSS-MMSI (RGB+Depth+Normal) Single Frame Semantic Segmentation Using Multi-Modal Spherical Images code — Compare
THUD Robotic Dataset (4 rows) SA-Gate Bi-directional Cross-Modality Feature Propagation with... code — Compare
CEMS-W (3 rows) UPerNet (RN50) Robust Burned Area Delineation through Multitask Learning code — Compare
dacl10k v1 testdev (3 rows) FPN EfficientNet-B4 w/ Aux loss dacl10k: Benchmark for Semantic Bridge Damage Segmentation code — Compare
DIVA-HisDB (3 rows) U-Net DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis code — Compare
Montgomery County X-ray Set (3 rows) UNETR + SS-CXR SPCXR: Self-supervised Pretraining using Chest X-rays Towards a... — — Compare
PASCAL VOC 2011 test (3 rows) Plugin network Plugin Networks for Inference under Partial Evidence code — Compare
PASTIS (3 rows) Exchanger+Mask2Former Revisiting the Encoding of Satellite Image Time Series code — Compare
Potsdam (3 rows) HRNet-48 Deep High-Resolution Representation Learning for Visual Recognition code Syntology 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified Compare
SIFT-flow (3 rows) RBE2E Region-based semantic segmentation with end-to-end training code — Compare
Stanford2D3D Panoramic - RGBD (3 rows) CBFC Complementary Bi-directional Feature Compression for Indoor 360°... — — Compare
SYNTHIA (3 rows) CGA-Net CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation code — Compare
US3D (3 rows) DeepLabV3+ Encoder-Decoder with Atrous Separable Convolution for Semantic... code Syntology community repositories only · 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified Compare
38-Cloud (2 rows) Cloud-Net+ Cloud and Cloud Shadow Segmentation for Remote Sensing Imagery via... code — Compare
AI-TOD (2 rows) Unet++(ResNet-50) UNet++: A Nested U-Net Architecture for Medical Image Segmentation code Syntology community repositories only · 21 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 1 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified Compare
ApolloScape (2 rows) ERFNet-IntRA-KD (ours) Inter-Region Affinity Distillation for Road Marking Segmentation code Syntology official (archive's flag): 4 ran · 4 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; 0 where Syntology's instrument failed) · 0 unverified Compare
Cityscapes (2 rows) SPFNet34M S²-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network... code — Compare
Cleargrasp (Novel) (2 rows) Cleargrasp ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation 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) · 5 unverified Compare
Endoscapes (2 rows) MoCo V2 Surg SSL - DeepLabv3+ head Dissecting Self-Supervised Learning Methods for Surgical Computer Vision code — Compare
Freiburg Forest (2 rows) SSMA Self-Supervised Model Adaptation for Multimodal Semantic Segmentation code — Compare
Graz-02 (2 rows) 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
HePIC 🏛️ (2 rows) BIM-Net++ Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation code — Compare
HERA RFI Detection (2 rows) Nearest Latent Neighbours RFI Detection with Spiking Neural Networks code — Compare
Kvasir-Instrument (2 rows) DoubleUNet DoubleU-Net: A Deep Convolutional Neural Network for Medical Image... 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: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
LOFAR RFI Detection (2 rows) Nearest Latent Neighbours RFI Detection with Spiking Neural Networks code — Compare
MUSES: MUlti-SEnsor Semantic perception dataset (2 rows) CAFuser (Swin-T) CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic... 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
PASCAL VOC 2007 (2 rows) GALDNet Global Aggregation then Local Distribution in Fully Convolutional Networks code Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 2 unverified Compare
PH2 (2 rows) MobileUNETR MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer... code — Compare
SkyScapes-Lane (2 rows) SkyScapesNet-Lane SkyScapes Fine-Grained Semantic Understanding of Aerial Scenes — — Compare
SYNTHIA-CVPR’16 (2 rows) SSMA Self-Supervised Model Adaptation for Multimodal Semantic Segmentation code — Compare
AIRS (1 row) ICT-Net Semantic Segmentation from Remote Sensor Data and the Exploitation... code — Compare
ARCH2S (1 row) BIM-Net Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation code — Compare
ATLANTIS (1 row) Erfani et al. ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images code — Compare
BDD (1 row) FasterSeg FasterSeg: Searching for Faster Real-time Semantic Segmentation code Syntology official (archive's flag): 8 ran · 11 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; 2 where Syntology's instrument failed) · 2 unverified Compare
Cam2BEV (1 row) uNetXST A Sim2Real Deep Learning Approach for the Transformation of Images... code Syntology official (archive's flag): 5 ran · 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 Compare
Cityscapes 3D (1 row) TaskPrompter Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection,... code — Compare
Cityscapes VIPriors subset (1 row) EfficientSeg EfficientSeg: An Efficient Semantic Segmentation Network code — Compare
COCO-Stuff (1 row) Deeplab v2 COCO-Stuff: Thing and Stuff Classes in Context code Syntology community repositories only · 8 ran (of which 0 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) · 21 unverified Compare
COCO-Stuff-27 (1 row) DiffSeg (512) Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation... 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) · 0 unverified Compare
COCO-Stuff full (1 row) SegFormer-B5 (Single Scale) SegFormer: Simple and Efficient Design for Semantic Segmentation... code Syntology official: no sample here; runs from other or unrecorded repositories · 66 ran (of which 22 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 14 where Syntology's instrument failed) · 20 unverified Compare
dacl10k v1 testfinal (1 row) FPN EfficientNet-B4 dacl10k: Benchmark for Semantic Bridge Damage Segmentation code — Compare
DeLiVER test (1 row) CAFuser CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic... 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
DroneDeploy (1 row) DLv3+ (Xception65) Aerial Imagery Pixel-level Segmentation code — Compare
Forward-Looking Sonar Marine Debris Datasets (1 row) Unet+RN34 The Marine Debris Dataset for Forward-Looking Sonar Semantic Segmentation code — Compare
FP4S (1 row) FP4S Floor Plan Image Segmentation Via Scribble-Based Semi-Weakly... code — Compare
HAM10000 (1 row) MFSNet MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation code — Compare
ISIC 2017 (1 row) MFSNet MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation code — Compare
LandCover.ai (1 row) U-Net (ConvFormer-M36) U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery — — Compare
ManipalUAVid (1 row) UVid-Net UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by... code — Compare
Mila Simulated Floods (1 row) FloodTransformer (Ours) Transformer-based Flood Scene Segmentation for Developing Countries — — Compare
MixedWM38 (1 row) WaferSegClassNet WaferSegClassNet -- A Light-weight Network for Classification and... code — Compare
OpenEDS (1 row) RITnet RITnet: Real-time Semantic Segmentation of the Eye for Gaze Tracking code — Compare
PASCAL VOC (1 row) SegCLIP SegCLIP: Patch Aggregation with Learnable Centers for... code — Compare
PASCAL VOC 2010 test (1 row) SIW Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings — — Compare
PASCAL VOC 2011 (1 row) DLDL-8s+CRF Deep Label Distribution Learning with Label Ambiguity code — Compare
PASCAL VOC 2012 (1 row) DLDL-8s+CRF Deep Label Distribution Learning with Label Ambiguity code — Compare
PASTIS-R (1 row) Late Fusion Multi-Modal Temporal Attention Models for Crop Mapping from... code — Compare
RUGD (1 row) GA-Nav GANav: Efficient Terrain Segmentation for Robot Navigation in... code — Compare
SBCoseg (1 row) Dice loss + IS-Triplet loss Improving Image co-segmentation via Deep Metric Learning — — Compare
SemanticPOSS (1 row) TFNet TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR... — — Compare
STARE (1 row) UNet U-Net: Convolutional Networks for Biomedical Image Segmentation code Syntology 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified Compare
SWIMSEG (1 row) ACLNet ACLNet: An Attention and Clustering-based Cloud Segmentation Network code — Compare
SWINSEG (1 row) ACLNet ACLNet: An Attention and Clustering-based Cloud Segmentation Network code — Compare
SWINySEG (1 row) ACLNet ACLNet: An Attention and Clustering-based Cloud Segmentation Network code — Compare
UTFPR-SBD3 (1 row) EPYNET EPYNET: Efficient Pyramidal Network for Clothing Segmentation — — Compare
WildDash (1 row) SIW Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings — — Compare
ADE20K-150 (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

347 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 347 until expanded.

COCO (Common Objects in Context)CityscapesKITTIShapeNetScanNetADE20KNYUv2DAVISEuroSATSYNTHIAS3DISSUN RGB-DBDD100KMatterport3DRefCOCOReplicaGTA5COCO-StuffPASCAL ContextDAVIS 2017KITTI-360CamVidVisDA-2017HAM10000HelenKvasir-SEGPASCAL VOCSUNCGLabelMePASCAL-5iYouTube-VIS 2019Objects365PartNet2D-3D-SSTAREVirtual KITTIMake3DPASCAL VOC 2007SUN3DKvasirPASCAL VOC 2012 testHypersimSegTrack-v2AVEMapillary Vistas DatasetIDDMedical Segmentation DecathlonBigEarthNetStructured3DPROMISE12iSAIDLoveDAReferItGameApolloScapeSemanticPOSSBraTS 2015CoNSePSemantic3DPlaces365LIPPanNukeDark ZurichLost and FoundRELLIS-3DWoodScapeUAVidVirtual KITTI 2xBD3D-FUTUREWildDashStanford BackgroundSynscapes3RScanDensePASSImageNet-SDDD17KITTI RoadRoadTracerSlakh2100WORDOpen Images V4STPLS3DPST900OxUvaSEN12MSSUIMTrans10KOpenEDSPhraseCutDeepFashion2InteriorNetOCIDPartImageNetSegTHORSensatUrbanGIDISIC 2018 Task 1ISPRS PotsdamNighttime DrivingScribbleSupIKEA ASMROSEDADA-segToronto-3DDeepWeedsDigestPathDSECHOI4DCARRADASatlasINRIA Aerial Image LabelingMSegAVSBenchFMB DatasetPASCAL VOC 2011DeepFishDELIVERFoodSeg103Hi4DISPRS VaihingenKvasir-InstrumentMCubeSModaNetAgriculture-VisionAI-TODCrossMoDAPASTISMoNuSegSceneNetCryoNuSegDADA-2000DIVA-HisDBParis-Lille-3DRoadAnomaly21FashionpediaMHPREFUGE ChallengeBraTS 2016Cityscapes 3DHM3DSemTTPLAWaterScenesPartial-iLIDSSemanticSTFTrashCanWildScenesLandCover.aiRailSem19SD-198So2Sat LCZ42TACO2-PM Vessel DatasetACDC ScribblesCropAndWeedFine-Grained Grass Segmentation DatasetPH2SpaceNet 2AIRSBIGBIMCV COVID-19EgoHOSEntitySegPerSegPhenoBenchSAMRSSketchySceneTSSBUIISDTTD-MobileEchonet-DynamicMontgomery County X-ray SetRIT-18SynthCityZJU-RGB-PNDD20OpenEDS2020OST300Plant Seedlings DatasetSunnybrook Cardiac DataEarthVQAFreiburg ForestGFFMatterportLayoutOpen Images V7SWIMSEGVDDXImageNet-1225kTreesBraTS 2014BUP20Cata7CC3M-TagMaskGolfDBIDDAISBDAKvasir-Sessile datasetLabPicsLaRSm2caiSegMarket1501-AttributesNERDS 360Rent3DSpaceNet 1SWINSEGTAS500UPLightWGISDZeroWasteAeroRITCrackVision12KDukeMTMC-attributeEDENEndoscapesFine-Grained Cloud Segmentation DatasetFLAIR (French Land cover from Aerospace ImageRy)MCubeS (P)Middlebury 2001MJU-WasteMUADMUSES: MUlti-SEnsor Semantic perception datasetPASTIS-RSWINySEGSwiss3DCitiesUSIS10KVLOG DatasetWISDOMAircraft Context DatasetAll-day CityScapesARCH2SBRIGHTCheXlocalizeDeepSportRadar-v1DOORSFive-Billion-PixelsHelixNetHephaestusImage and Video AdvertisementsKvasirCapsule-SEGMedico automatic polyp segmentation challenge (dataset)OAM-TCDOpenTTGamesPETRAWPICRobotPushRuralscapesSpaceNet MVOIUNDDVocalFoldsATLANTISCalCROP21Cam2BEVCityscapes VIPriors subsetColorectal AdenomaCumulodacl10kEMDS-6Endotect Polyp Segmentation Challenge DatasetExtended Agriculture-VisionForward-Looking Sonar Marine Debris DatasetsFPDSFracAtlasG-VUEHERA RFI DetectionHuTicsLOFAR RFI DetectionLombardia Sentinel-2 Image Time Series for Crop MappingMagicBathyNetMila Simulated FloodsMUSICMVTec D2SNVGazeOADATODMSOmniCityPAX-Ray++Photi-LakeIcePothole MixPotsdamRetinal MicrosurgeryRoad Scene GraphRUGDSB20SegRCDBSemanticSpray DatasetTAS-NIRTopology Optimization DatasetU-DIADS-BibVistas-NPBCSDBurned Area Delineation from Satellite ImageryCARLA2RealCCSECEMS-WCiona17CongNaMulCUTSDADEDroneDeployEBHI-SegFP4SFreiburg TerrainsGUISS datasetHASCDHePIC 🏛️HuTu 80IndraEyeIntegrated Drone Dataset for Semantic SegmentationLIB-HSIMeta OmniumMixedWM38MLSMOSADMTNeuroMulti-species fruit flower detection datasetsMultispectral and HD vineyard orthomosaics from central PortugalOkutama Drone and Swiss Drone DatasetPanoramic Video Panoptic Segmentation DatasetPolyp ASHRisk-Aware Planning DatasetSBCosegSemantic Segmentation Vineyard RowsSemanticSugarBeetsSemanticUSLSen4AgriNetSYNTHIA-PANOThe RobotriXThermal Face DatabaseTimberVisionTintoTransProteusUncertainty Quantification for Underwater Object SegmentationUTFPR-SBD3VizWiz-FewShotXKCDColorsAachen-Heerlen Annotated Steel Microstructure DatasetCorn Seeds DatasetDMSDronescapesLemons quality control datasetMVP-24KOCT5kOpenSurfacesOUTBACK: A Multimodal Synthetic Dataset for Rural Australian Off-road Robot NavigationPAXRayPSIEUAV-based multispectral vineyardsWTA/TLA

Subtasks archive 2025-07-28

29 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 14,763 · with a code link: 6,644 · where Syntology ran a sample: 1,583 (1,345 with a run with no instrument failure, 238 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1,583 of 14,763 tagged: 1,345 with a run with no instrument failure, 238 where every run was a failure of Syntology's instrument)

Page 1 of 148: papers 1 to 100 of 14,763, 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 89 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