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 101125 of 2262 papers

TitleStatusHype
Dilated Neighborhood Attention TransformerCode2
Mask2Former for Video Instance SegmentationCode2
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative DataCode2
Mask-Free Video Instance SegmentationCode2
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based TrainingCode2
DreamColour: Controllable Video Colour Editing without TrainingCode2
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous ConvolutionCode2
Occlusion-Aware Instance Segmentation via BiLayer Network ArchitecturesCode2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
DiffusionInst: Diffusion Model for Instance SegmentationCode2
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance SegmentationCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
P2Object: Single Point Supervised Object Detection and Instance SegmentationCode2
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion ModelsCode2
PartSTAD: 2D-to-3D Part Segmentation Task AdaptationCode2
DaViT: Dual Attention Vision TransformersCode2
Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded ScenesCode2
RelationField: Relate Anything in Radiance FieldsCode2
Revisiting Contrastive Methods for Unsupervised Learning of Visual RepresentationsCode2
RMT: Retentive Networks Meet Vision TransformersCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
Scene-Centric Unsupervised Panoptic SegmentationCode2
Segment Anything for HistopathologyCode2
Deep Snake for Real-Time Instance SegmentationCode2
Show:102550
← PrevPage 5 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
8GLEE-Promask AP54.2Unverified
9ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified