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 601650 of 2262 papers

TitleStatusHype
Distilling Knowledge via Knowledge ReviewCode1
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained FeaturesCode1
Advanced Deep Networks for 3D Mitochondria Instance SegmentationCode1
HoughNet: Integrating near and long-range evidence for visual detectionCode1
Zero-Shot Instance SegmentationCode1
Crossover Learning for Fast Online Video Instance SegmentationCode1
Co-Scale Conv-Attentional Image TransformersCode1
DropLoss for Long-Tail Instance SegmentationCode1
Pointly-Supervised Instance SegmentationCode1
Common Limitations of Image Processing Metrics: A Picture StoryCode1
Visiting the Invisible: Layer-by-Layer Completed Scene DecompositionCode1
Look Closer to Segment Better: Boundary Patch Refinement for Instance SegmentationCode1
Location-Sensitive Visual Recognition with Cross-IOU LossCode1
Contour Proposal Networks for Biomedical Instance SegmentationCode1
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance SegmentationCode1
Scale-aware Automatic Augmentation for Object DetectionCode1
FAPIS: A Few-shot Anchor-free Part-based Instance SegmenterCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic SegmentationCode1
Sparse Object-level Supervision for Instance Segmentation with Pixel EmbeddingsCode1
Video Instance Segmentation with a Propose-Reduce ParadigmCode1
Region Similarity Representation LearningCode1
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayersCode1
Scaling Local Self-Attention for Parameter Efficient Visual BackbonesCode1
Video Class Agnostic Segmentation Benchmark for Autonomous DrivingCode1
SG-Net: Spatial Granularity Network for One-Stage Video Instance SegmentationCode1
LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud SegmentationCode1
Track to Detect and Segment: An Online Multi-Object TrackerCode1
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance SegmentationCode1
Unknown Object Segmentation from Stereo ImagesCode1
Spatially Consistent Representation LearningCode1
Quality-Aware Network for Human ParsingCode1
Cross-View Regularization for Domain Adaptive Panoptic SegmentationCode1
InstantDL-An easy-to-use deep learning pipeline for image segmentation and classificationCode1
FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance SegmentationCode1
Simple multi-dataset detectionCode1
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without ConvolutionsCode1
Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-CaseCode1
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object DetectionCode1
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection ConsistencyCode1
Occluded Video Instance Segmentation: A BenchmarkCode1
SA-Net: Shuffle Attention for Deep Convolutional Neural NetworksCode1
Embedding-based Instance Segmentation in MicroscopyCode1
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized LabelsCode1
Superpixel-based Refinement for Object Proposal GenerationCode1
CryoNuSeg: A Dataset for Nuclei Instance Segmentation of Cryosectioned H&E-Stained Histological ImagesCode1
AggMask: Exploring locally aggregated learning of mask representations for instance segmentationCode1
Continuous Copy-Paste for One-Stage Multi-Object Tracking and SegmentationCode1
CDNet: Centripetal Direction Network for Nuclear Instance SegmentationCode1
Show:102550
← PrevPage 13 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
8GLEE-Promask AP54.2Unverified
9ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2Unverified
10SwinV2-G (HTC++)mask AP53.7Unverified