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

Showing 110 of 2262 papers

TitleStatusHype
SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance SegmentationCode0
Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping1
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation0
SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning0
Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation0
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 Understanding0
Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment0
A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects0
Show:102550
← PrevPage 1 of 227Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Swin-T (ImageNet-1k pretrain)Average Recall@IoU:0.5-0.9528Unverified
2Mask R-CNN (ResNet-50-FPN, ImageNet-1k pretrain)Average Recall@IoU:0.5-0.9521.9Unverified
3Swin-TAverage Recall@IoU:0.5-0.9520.6Unverified
4Mask R-CNN (ResNet-50-FPN)Average Recall@IoU:0.5-0.9520.1Unverified
5Wahn Mask R-CNNAverage Recall@IoU:0.5-0.959.4Unverified