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 751800 of 2262 papers

TitleStatusHype
EfficientPS: Efficient Panoptic SegmentationCode1
PointGroup: Dual-Set Point Grouping for 3D Instance SegmentationCode1
Look-into-Object: Self-supervised Structure Modeling for Object RecognitionCode1
What Deep CNNs Benefit from Global Covariance Pooling: An Optimization PerspectiveCode1
Scalable learning for bridging the species gap in image-based plant phenotypingCode1
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention FusionCode1
CentripetalNet: Pursuing High-quality Keypoint Pairs for Object DetectionCode1
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in VideosCode1
1st Place Solutions for OpenImage2019 -- Object Detection and Instance SegmentationCode1
TACO: Trash Annotations in Context for Litter DetectionCode1
Conditional Convolutions for Instance SegmentationCode1
Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point CloudsCode1
Learning in the Frequency DomainCode1
Algorithm-hardware Co-design for Deformable ConvolutionCode1
Key Points Estimation and Point Instance Segmentation Approach for Lane DetectionCode1
Panoptic Feature Fusion Net: A Novel Instance Segmentation Paradigm for Biomedical and Biological ImagesCode1
SpotNet: Self-Attention Multi-Task Network for Object DetectionCode1
Segmenting Unseen Industrial Components in a Heavy Clutter Using RGB-D Fusion and Synthetic DataCode1
FourierNet: Compact mask representation for instance segmentation using differentiable shape decodersCode1
PatchPerPix for Instance SegmentationCode1
BlendMask: Top-Down Meets Bottom-Up for Instance SegmentationCode1
Towards Accurate Post-training Network Quantization via Bit-Split and StitchingCode1
Instance-wise Depth and Motion Learning from Monocular VideosCode1
PointRend: Image Segmentation as RenderingCode1
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image SegmentationCode1
SOLO: Segmenting Objects by LocationsCode1
Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-PickingCode1
Weakly Supervised Cell Instance Segmentation by Propagating from Detection ResponseCode1
CenterMask : Real-Time Anchor-Free Instance SegmentationCode1
Classification Calibration for Long-tail Instance SegmentationCode1
SpatialFlow: Bridging All Tasks for Panoptic SegmentationCode1
PolarMask: Single Shot Instance Segmentation with Polar RepresentationCode1
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and ResolutionCode1
Global Aggregation then Local Distribution in Fully Convolutional NetworksCode1
Deep High-Resolution Representation Learning for Visual RecognitionCode1
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature FusionCode1
LVIS: A Dataset for Large Vocabulary Instance SegmentationCode1
Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering BandwidthCode1
MMDetection: Open MMLab Detection Toolbox and BenchmarkCode1
Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask TransferCode1
Learning Object Bounding Boxes for 3D Instance Segmentation on Point CloudsCode1
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale AmbiguitiesCode1
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial ImagesCode1
Weakly Supervised Learning of Instance Segmentation with Inter-pixel RelationsCode1
YOLACT: Real-time Instance SegmentationCode1
Res2Net: A New Multi-scale Backbone ArchitectureCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
Augmentation for small object detectionCode1
Hybrid Task Cascade for Instance SegmentationCode1
Slimmable Neural NetworksCode1
Show:102550
← PrevPage 16 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
8ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
9GLEE-Promask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified