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 501550 of 2262 papers

TitleStatusHype
D2Det: Towards High Quality Object Detection and Instance SegmentationCode1
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-RefinementCode1
AISFormer: Amodal Instance Segmentation with TransformerCode1
LeafMask: Towards Greater Accuracy on Leaf SegmentationCode1
Learn Fast, Segment Well: Fast Object Segmentation Learning on the iCub RobotCode1
Learn from Foundation Model: Fruit Detection Model without Manual AnnotationCode1
PolyLoss: A Polynomial Expansion Perspective of Classification Loss FunctionsCode1
Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance SegmentationCode1
Learning Equivariant Segmentation with Instance-Unique QueryingCode1
Learning Gaussian Instance Segmentation in Point CloudsCode1
DVIS++: Improved Decoupled Framework for Universal Video SegmentationCode1
DVIS: Decoupled Video Instance Segmentation FrameworkCode1
DropLoss for Long-Tail Instance SegmentationCode1
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic ConvolutionCode1
Look Closer to Segment Better: Boundary Patch Refinement for Instance SegmentationCode1
Amodal Intra-class Instance Segmentation: Synthetic Datasets and BenchmarkCode1
DynaMask: Dynamic Mask Selection for Instance SegmentationCode1
Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance SegmentationCode1
3D Instances as 1D KernelsCode1
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN TrainingCode1
Long-tailed Instance Segmentation using Gumbel Optimized LossCode1
Look-into-Object: Self-supervised Structure Modeling for Object RecognitionCode1
DoNet: Deep De-overlapping Network for Cytology Instance SegmentationCode1
Learning Dynamic Query Combinations for Transformer-based Object Detection and SegmentationCode1
Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater EnvironmentCode1
Benchmarking Self-Supervised Learning on Diverse Pathology DatasetsCode1
DocSegTr: An Instance-Level End-to-End Document Image Segmentation TransformerCode1
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal EffectCode1
Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context TermsCode1
LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution KernelsCode1
Location-Sensitive Visual Recognition with Cross-IOU LossCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Dynamic Convolution for 3D Point Cloud Instance SegmentationCode1
LIVECell—A large-scale dataset for label-free live cell segmentationCode1
Long-tail Detection with Effective Class-MarginsCode1
Long-tailed Distribution AdaptationCode1
Low Latency Instance Segmentation by Continuous Clustering for LiDAR SensorsCode1
Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2Code1
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance SegmentationCode1
LGD: Label-guided Self-distillation for Object DetectionCode1
DilateFormer: Multi-Scale Dilated Transformer for Visual RecognitionCode1
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware AlignmentCode1
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningCode1
DeVIS: Making Deformable Transformers Work for Video Instance SegmentationCode1
3D Indoor Instance Segmentation in an Open-WorldCode1
Distilling Knowledge via Knowledge ReviewCode1
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayersCode1
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise BinarizationCode1
Deep Learning based Food Instance Segmentation using Synthetic DataCode1
DFormer: Diffusion-guided Transformer for Universal Image SegmentationCode1
Show:102550
← PrevPage 11 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