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 701725 of 2262 papers

TitleStatusHype
TIDE: A General Toolbox for Identifying Object Detection ErrorsCode1
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance SegmentationCode1
Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor SceneCode1
Learning with Noisy Class Labels for Instance SegmentationCode1
Supervised Edge Attention Network for Accurate Image Instance SegmentationCode1
Learning RGB-D Feature Embeddings for Unseen Object Instance SegmentationCode1
SipMask: Spatial Information Preservation for Fast Image and Video Instance SegmentationCode1
Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and trackingCode1
Detection and Segmentation of Custom Objects using High Distraction Photorealistic Synthetic DataCode1
Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance SegmentationCode1
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance SegmentationCode1
Representation Sharing for Fast Object Detector Search and BeyondCode1
Deep Variational Instance SegmentationCode1
Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance SegmentationCode1
Balanced Meta-Softmax for Long-Tailed Visual RecognitionCode1
Learning Gaussian Instance Segmentation in Point CloudsCode1
Boundary-preserving Mask R-CNNCode1
RepPoints V2: Verification Meets Regression for Object DetectionCode1
Unseen Object Instance Segmentation for Robotic EnvironmentsCode1
Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric LearningCode1
Point-Set Anchors for Object Detection, Instance Segmentation and Pose EstimationCode1
PointTrack++ for Effective Online Multi-Object Tracking and SegmentationCode1
Rethinking Channel Dimensions for Efficient Model DesignCode1
MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial VideosCode1
Video Panoptic SegmentationCode1
Show:102550
← PrevPage 29 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