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 301325 of 2262 papers

TitleStatusHype
SAM-Path: A Segment Anything Model for Semantic Segmentation in Digital PathologyCode1
Towards accurate instance segmentation in large-scale LiDAR point cloudsCode1
MobileViG: Graph-Based Sparse Attention for Mobile Vision ApplicationsCode1
High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error RefinementCode1
PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and AggregationCode1
Segmentation and Tracking of Vegetable Plants by Exploiting Vegetable Shape Feature for Precision Spray of Agricultural RobotsCode1
Inter-Instance Similarity Modeling for Contrastive LearningCode1
Primitive Generation and Semantic-related Alignment for Universal Zero-Shot SegmentationCode1
VISION Datasets: A Benchmark for Vision-based InduStrial InspectiONCode1
Revisiting Token Pruning for Object Detection and Instance SegmentationCode1
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive FusionCode1
PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural DomainCode1
DVIS: Decoupled Video Instance Segmentation FrameworkCode1
DFormer: Diffusion-guided Transformer for Universal Image SegmentationCode1
Asymmetric Patch Sampling for Contrastive LearningCode1
Cyclic Learning: Bridging Image-level Labels and Nuclei Instance SegmentationCode1
A Robust Feature Downsampling Module for Remote Sensing Visual TasksCode1
OpenVIS: Open-vocabulary Video Instance SegmentationCode1
Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance SegmentationCode1
Explain Any Concept: Segment Anything Meets Concept-Based ExplanationCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection from Aerial ImagesCode1
Thermal Bridges on Building RooftopsCode1
SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance SegmentationCode1
CLUSTSEG: Clustering for Universal SegmentationCode1
Show:102550
← PrevPage 13 of 91Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-HAP5080.8Unverified
2ResNeSt-200 (multi-scale)AP5070.2Unverified
3CenterMask + VoVNetV2-99 (multi-scale)AP5066.2Unverified
4CenterMask + VoVNetV2-57 (single-scale)AP5060.8Unverified
5Co-DETRmask AP57.1Unverified
6CBNetV2 (EVA02, single-scale)mask AP56.1Unverified
7ISDA (ResNet-50)APL55.7Unverified
8EVAmask AP55.5Unverified
9FD-SwinV2-Gmask AP55.4Unverified
10Mask Frozen-DETRmask AP55.3Unverified
#ModelMetricClaimedVerifiedStatus
1InternImage-BGFLOPs501Unverified
2Co-DETRmask AP56.6Unverified
3ViT-CoMer-L (Mask RCNN, DINOv2)mask AP55.9Unverified
4InternImage-Hmask AP55.4Unverified
5EVAmask AP55Unverified
6Mask Frozen-DETRmask AP54.9Unverified
7MasK DINO (SwinL, multi-scale)mask AP54.5Unverified
8ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
9GLEE-Promask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified