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 201250 of 2262 papers

TitleStatusHype
Conditional Convolutions for Instance SegmentationCode1
Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance SegmentationCode1
Common Limitations of Image Processing Metrics: A Picture StoryCode1
Compositional Human-Scene Interaction Synthesis with Semantic ControlCode1
A Structure-Aware Relation Network for Thoracic Diseases Detection and SegmentationCode1
Complete Instances Mining for Weakly Supervised Instance SegmentationCode1
EDAPS: Enhanced Domain-Adaptive Panoptic SegmentationCode1
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale AmbiguitiesCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Container: Context Aggregation NetworkCode1
Context-Aware Relative Object Queries To Unify Video Instance and Panoptic SegmentationCode1
Asymmetric Patch Sampling for Contrastive LearningCode1
Dynamic Convolution for 3D Point Cloud Instance SegmentationCode1
Contextual Transformer Networks for Visual RecognitionCode1
DynaMask: Dynamic Mask Selection for Instance SegmentationCode1
A Tri-Layer Plugin to Improve Occluded DetectionCode1
Contour Proposal Networks for Biomedical Instance SegmentationCode1
DVIS++: Improved Decoupled Framework for Universal Video SegmentationCode1
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable ApproachCode1
Attention-Based Transformers for Instance Segmentation of Cells in MicrostructuresCode1
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic ConvolutionCode1
1st Place Solutions for OpenImage2019 -- Object Detection and Instance SegmentationCode1
Coherent Reconstruction of Multiple Humans from a Single ImageCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
Audio-Visual Instance SegmentationCode1
Augmentation for small object detectionCode1
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayersCode1
Co-Scale Conv-Attentional Image TransformersCode1
AugmenTory: A Fast and Flexible Polygon Augmentation LibraryCode1
COVID-CT-Mask-Net: Prediction of COVID-19 from CT Scans Using Regional FeaturesCode1
A Generalized Framework for Video Instance SegmentationCode1
Crossover Learning for Fast Online Video Instance SegmentationCode1
Efficient Multi-Task RGB-D Scene Analysis for Indoor EnvironmentsCode1
Cross-View Regularization for Domain Adaptive Panoptic SegmentationCode1
Eigencontours: Novel Contour Descriptors Based on Low-Rank ApproximationCode1
AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D ScansCode1
CTVIS: Consistent Training for Online Video Instance SegmentationCode1
End-to-End Human Instance MattingCode1
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-EncodersCode1
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
D2Det: Towards High Quality Object Detection and Instance SegmentationCode1
Cyclic Learning: Bridging Image-level Labels and Nuclei Instance SegmentationCode1
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance SegmentationCode1
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural NetworkCode1
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object DetectionCode1
ASF-YOLO: A Novel YOLO Model with Attentional Scale Sequence Fusion for Cell Instance SegmentationCode1
AIO-P: Expanding Neural Performance Predictors Beyond Image ClassificationCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
DoNet: Deep De-overlapping Network for Cytology Instance SegmentationCode1
Show:102550
← PrevPage 5 of 46Next →

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
8GLEE-Promask AP54.2Unverified
9ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified