Browse State-of-the-Art › Instance Segmentation

Instance Segmentation

1,158 papers with code · 36 benchmarks · 111 datasets archive 2025-07-28

Computer Vision

Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.

Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

36 leaderboard tables shown for this task, 36 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 36 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): COCO minival (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
COCO test-dev (112 rows) Co-DETR DETRs with Collaborative Hybrid Assignments Training code Syntology 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) · 1 unverified Compare
COCO minival (93 rows) Co-DETR DETRs with Collaborative Hybrid Assignments Training code Syntology 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) · 1 unverified Compare
LVIS v1.0 val (25 rows) Co-DETR (single-scale) DETRs with Collaborative Hybrid Assignments Training code Syntology 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) · 1 unverified Compare
Cityscapes val (17 rows) ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) The Missing Point in Vision Transformers for Universal Image Segmentation code — Compare
ADE20K val (14 rows) OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained) OneFormer: One Transformer to Rule Universal Image Segmentation code Syntology official (archive's flag): 4 ran · 4 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; 2 where Syntology's instrument failed) · 1 unverified Compare
Cityscapes test (11 rows) Deep Watershed Transform Deep Watershed Transform for Instance Segmentation code Syntology 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) · 7 unverified Compare
ARMBench (7 rows) RISE (VIT-B) Robot Instance Segmentation with Few Annotations for Grasping code — Compare
Occluded COCO (6 rows) Swin-B + Cascade Mask R-CNN (tri-layer modelling) A Tri-Layer Plugin to Improve Occluded Detection code — Compare
Separated COCO (6 rows) Swin-B + Cascade Mask R-CNN (tri-layer modelling) A Tri-Layer Plugin to Improve Occluded Detection code — Compare
iSAID (5 rows) PANet++ iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images 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
TBBR (5 rows) Swin-T (ImageNet-1k pretrain) Deep learning approaches to building rooftop thermal bridge... code — Compare
BDD100K val (4 rows) Mask Transfiner Mask Transfiner for High-Quality Instance Segmentation 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
COCO 2017 val (4 rows) SparK (ConvNeXt V1-B Mask R-CNN) Designing BERT for Convolutional Networks: Sparse and Hierarchical... code Syntology official (archive's flag): 9 ran · 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
COCO val (panoptic labels) (4 rows) OneFormer (InternImage-H, emb_dim=1024, single-scale) OneFormer: One Transformer to Rule Universal Image Segmentation code Syntology official (archive's flag): 4 ran · 4 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; 2 where Syntology's instrument failed) · 1 unverified Compare
OoDIS (3 rows) UGainS UGainS: Uncertainty Guided Anomaly Instance Segmentation code — Compare
NYUDv2-IS (2 rows) IAM + SOLQ IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks code — Compare
SUN-RGBD-IS (2 rows) IAM + SOLQ IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks code — Compare
UIIS (2 rows) WaterMask RCNN WaterMask: Instance Segmentation for Underwater Imagery code — Compare
Box-IS (1 row) IAM + SOLQ IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks code — Compare
Cityscapes (1 row) CAST CAST: Contrastive Adaptation and Distillation for Semi-Supervised... — — Compare
COCO (1 row) ColorMAE-Green-ViTB-1600 ColorMAE: Exploring data-independent masking strategies in Masked... code — Compare
coco minval (1 row) R3-CNN (ResNet-50-FPN, GC-Net) Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing code — Compare
COCO-N Medium (1 row) Mask R-CNN ResNet-50 FPN Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters code Syntology official (archive's flag): 2 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) · 0 unverified Compare
COCO val2017 (1 row) MogaNet-S (256x192) MogaNet: Multi-order Gated Aggregation Network code Syntology official (archive's flag): 12 ran · 12 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified Compare
iShape (1 row) ASIS(baseline) iShape: A First Step Towards Irregular Shape Instance Segmentation — — Compare
KINS (1 row) BCNet Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers 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: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified Compare
LDD (1 row) R^3-CNN LDD: A Dataset for Grape Diseases Object Detection and Instance... — — Compare
Leaf Segmentation Challenge (1 row) LeafMask LeafMask: Towards Greater Accuracy on Leaf Segmentation code — Compare
LVIS v1.0 test-dev (1 row) R50-FPN-MaskRCNN-TTA 1st Place Solution of LVIS Challenge 2020: A Good Box is not a... — — Compare
nuScenes (1 row) TraDeS Track to Detect and Segment: An Online Multi-Object Tracker code Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 0 unverified Compare
NYU Depth v2 (1 row) SGPN-CNN SGPN: Similarity Group Proposal Network for 3D Point Cloud... code — Compare
PartNet (1 row) PE Point Cloud Instance Segmentation using Probabilistic Embeddings — — Compare
TexBiG 2022 test (1 row) VSR (Vison, Semantics and Relation Model) A Dataset for Analysing Complex Document Layouts in the Digital... code — Compare
TexBiG 2023 test (1 row) DetectoRS + LAEM Drawing the Same Bounding Box Twice? Coping Noisy Annotations in... code — Compare
UAVBillboards (1 row) YOLOv8-X Mapping urban large-area advertising structures using drone... code — Compare
UFBA-425 (1 row) BB-UNet Instance Segmentation and Teeth Classification in Panoramic X-rays code — Compare

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

111 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 111 until expanded.

Subtasks archive 2025-07-28

17 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 2,262 · with a code link: 1,158 · where Syntology ran a sample: 324 (282 with a run with no instrument failure, 42 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (324 of 2,262 tagged: 282 with a run with no instrument failure, 42 where every run was a failure of Syntology's instrument)

Page 1 of 23: papers 1 to 100 of 2,262, 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 71 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