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 22012250 of 2262 papers

TitleStatusHype
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANsCode1
Learning to Segment Every ThingCode0
Exploiting the potential of unlabeled endoscopic video data with self-supervised learning0
Distance to Center of Mass Encoding for Instance SegmentationCode0
Deep Extreme Cut: From Extreme Points to Object SegmentationCode0
SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance SegmentationCode0
S4Net: Single Stage Salient-Instance SegmentationCode0
Non-local Neural NetworksCode1
Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulation0
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes0
SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?0
SGN: Sequential Grouping Networks for Instance Segmentation0
Bounding Boxes, Segmentations and Object Coordinates: How Important Is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?0
Semi-Supervised Hierarchical Semantic Object Parsing0
Playing for Benchmarks0
Efficient Column Generation for Cell Detection and Segmentation0
Leveraging multiple datasets for deep leaf counting0
Semantic Instance Segmentation with a Discriminative Loss FunctionCode0
Fast Scene Understanding for Autonomous DrivingCode0
Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes0
Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos0
Deep GrabCut for Object Selection0
Indoor Scene Parsing With Instance Segmentation, Semantic Labeling and Support Relationship Inference0
Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple ObjectsCode0
BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks0
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and SemanticsCode1
Towards Instance Segmentation with Object Priority: Prominent Object Detection and Recognition0
Instance-Level Salient Object Segmentation0
Pixelwise Instance Segmentation with a Dynamically Instantiated NetworkCode0
Pose2Instance: Harnessing Keypoints for Person Instance Segmentation0
Bootstrapping Labelled Dataset Construction for Cow Tracking and Behavior Analysis0
Semantic Instance Segmentation via Deep Metric LearningCode0
Mask R-CNNCode1
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground TruthCode0
Boundary-aware Instance Segmentation0
Learning Video Object Segmentation from Static ImagesCode0
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing0
TorontoCity: Seeing the World with a Million Eyes0
Efficient Pose and Cell Segmentation using Column Generation0
Object Detection Free Instance Segmentation With Labeling Transformations0
Deep Watershed Transform for Instance SegmentationCode0
Fully Convolutional Instance-aware Semantic SegmentationCode2
Gland Instance Segmentation Using Deep Multichannel Neural Networks0
Associative Embedding: End-to-End Learning for Joint Detection and GroupingCode0
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data0
Bottom-up Instance Segmentation using Deep Higher-Order CRFs0
Gland Instance Segmentation by Deep Multichannel Neural Networks0
Gland Instance Segmentation by Deep Multichannel Side Supervision0
End-to-End Instance Segmentation with Recurrent AttentionCode0
Bridging Category-level and Instance-level Semantic Image Segmentation0
Show:102550
← PrevPage 45 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