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 11011125 of 2262 papers

TitleStatusHype
NOISe: Nuclei-Aware Osteoclast Instance Segmentation for Mouse-to-Human Domain TransferCode0
GUNNEL: Guided Mixup Augmentation and Multi-View Fusion for Aquatic Animal SegmentationCode0
Learning Rich Features from RGB-D Images for Object Detection and SegmentationCode0
Multi-scale Cell Instance Segmentation with Keypoint Graph based Bounding BoxesCode0
Learning Regional Purity for Instance Segmentation on 3D Point CloudsCode0
Learning Panoptic Segmentation from Instance ContoursCode0
DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports ScenesCode0
Deep Spectral Improvement for Unsupervised Image Instance SegmentationCode0
MSN: Efficient Online Mask Selection Network for Video Instance SegmentationCode0
Monocular Depth Estimation Using Cues Inspired by Biological Vision SystemsCode0
Learning Instance Segmentation by InteractionCode0
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is ComingCode0
Learning Instance Occlusion for Panoptic SegmentationCode0
Benchmarking Label Noise in Instance Segmentation: Spatial Noise MattersCode0
Accurate Fine-grained Layout Analysis for the Historical Tibetan Document Based on the Instance SegmentationCode0
MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor PerceptionCode0
Learning deep structured active contours end-to-endCode0
Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance SegmentationCode0
Deep Level Set for Box-supervised Instance Segmentation in Aerial ImagesCode0
Learning a Spatio-Temporal Embedding for Video Instance SegmentationCode0
Deep Learning for Morphological Identification of Extended Radio Galaxies using Weak LabelsCode0
Learning to Cluster for Proposal-Free Instance SegmentationCode0
LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable AttentionCode0
MCA: Moment Channel Attention NetworksCode0
Layered Embeddings for Amodal Instance SegmentationCode0
Show:102550
← PrevPage 45 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