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 426450 of 2262 papers

TitleStatusHype
Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data AugmentationCode1
Instance Brownian Bridge as Texts for Open-vocabulary Video Instance SegmentationCode1
CompFeat: Comprehensive Feature Aggregation for Video Instance SegmentationCode1
Complete Instances Mining for Weakly Supervised Instance SegmentationCode1
BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online PoliciesCode1
BlendMask: Top-Down Meets Bottom-Up for Instance SegmentationCode1
Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2Code1
A Tri-Layer Plugin to Improve Occluded DetectionCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and ResolutionCode1
Deep Learning based Food Instance Segmentation using Synthetic DataCode1
Mask4Former: Mask Transformer for 4D Panoptic SegmentationCode1
Conditional Object-Centric Learning from VideoCode1
DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality AnnotationsCode1
InstanceFormer: An Online Video Instance Segmentation FrameworkCode1
Attention-Based Transformers for Instance Segmentation of Cells in MicrostructuresCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
Decoupling Classifier for Boosting Few-shot Object Detection and Instance SegmentationCode1
Container: Context Aggregation NetworkCode1
Container: Context Aggregation NetworksCode1
A Close Look at Spatial Modeling: From Attention to ConvolutionCode1
Deep Structured Instance Graph for Distilling Object DetectorsCode1
Context-Aware Relative Object Queries To Unify Video Instance and Panoptic SegmentationCode1
Indoor Panorama Planar 3D Reconstruction via Divide and ConquerCode1
Show:102550
← PrevPage 18 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