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 551575 of 2262 papers

TitleStatusHype
Towards unconstrained joint hand-object reconstruction from RGB videosCode1
Real-time Human-Centric Segmentation for Complex Video ScenesCode1
SOTR: Segmenting Objects with TransformersCode1
LeafMask: Towards Greater Accuracy on Leaf SegmentationCode1
Hierarchical Aggregation for 3D Instance SegmentationCode1
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode1
Improving Video Instance Segmentation via Temporal Pyramid RoutingCode1
Contextual Transformer Networks for Visual RecognitionCode1
Rank & Sort Loss for Object Detection and Instance SegmentationCode1
CycleMLP: A MLP-like Architecture for Dense PredictionCode1
Improving Mask R-CNN for Nuclei Instance Segmentation in Hematoxylin & Eosin-Stained Histological ImagesCode1
Dynamic Convolution for 3D Point Cloud Instance SegmentationCode1
Deep Learning based Food Instance Segmentation using Synthetic DataCode1
Visual Parser: Representing Part-whole Hierarchies with TransformersCode1
NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter ScaleCode1
Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context TermsCode1
Capturing, Reconstructing, and Simulating: the UrbanScene3D DatasetCode1
On Model Calibration for Long-Tailed Object Detection and Instance SegmentationCode1
CBNet: A Composite Backbone Network Architecture for Object DetectionCode1
Focal Self-attention for Local-Global Interactions in Vision TransformersCode1
K-Net: Towards Unified Image SegmentationCode1
Indoor Panorama Planar 3D Reconstruction via Divide and ConquerCode1
Real-time Instance Segmentation with Discriminative Orientation MapsCode1
P2T: Pyramid Pooling Transformer for Scene UnderstandingCode1
Tracking Instances as QueriesCode1
Show:102550
← PrevPage 23 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