SOTAVerified

Instance Segmentation

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 2262 papers

TitleStatusHype
SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance SegmentationCode0
Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping—0
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation—0
SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning—0
Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation—0
No time to train! Training-Free Reference-Based Instance SegmentationCode3
NOCTIS: Novel Object Cyclic Threshold based Instance SegmentationCode0
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding—0
Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment—0
A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects—0
Show:102550
← PrevPage 1 of 227Next →
All datasetsCOCO test-devCOCO minivalLVIS v1.0 valCityscapes valADE20K valARMBenchOccluded COCOOoDISSeparated COCOTBBRBDD100K valCOCO val (panoptic labels)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OneFormer (InternImage-H, emb_dim=1024, single-scale)AP52—Unverified
2OneFormer (DiNAT-L, single-scale)AP49.2—Unverified
3Mask2Former (Swin-L, single-scale)AP49.1—Unverified
4OneFormer (Swin-L, single-scale)AP49—Unverified