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 151200 of 2262 papers

TitleStatusHype
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode2
CompFeat: Comprehensive Feature Aggregation for Video Instance SegmentationCode1
AISFormer: Amodal Instance Segmentation with TransformerCode1
Complete Instances Mining for Weakly Supervised Instance SegmentationCode1
Common Limitations of Image Processing Metrics: A Picture StoryCode1
AIO-P: Expanding Neural Performance Predictors Beyond Image ClassificationCode1
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionCode1
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable ApproachCode1
Compositional Human-Scene Interaction Synthesis with Semantic ControlCode1
Coherent Reconstruction of Multiple Humans from a Single ImageCode1
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance SegmentationCode1
DIOD: Self-Distillation Meets Object DiscoveryCode1
Distilling Knowledge via Knowledge ReviewCode1
Clustering Plotted Data by Image SegmentationCode1
HCFormer: Unified Image Segmentation with Hierarchical ClusteringCode1
CLUSTSEG: Clustering for Universal SegmentationCode1
AggMask: Exploring locally aggregated learning of mask representations for instance segmentationCode1
A Generalized Framework for Video Instance SegmentationCode1
Conditional Convolutions for Instance SegmentationCode1
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance SegmentationCode1
DeVIS: Making Deformable Transformers Work for Video Instance SegmentationCode1
Affinity Attention Graph Neural Network for Weakly Supervised Semantic SegmentationCode1
ClusterFormer: Clustering As A Universal Visual LearnerCode1
DFormer: Diffusion-guided Transformer for Universal Image SegmentationCode1
DilateFormer: Multi-Scale Dilated Transformer for Visual RecognitionCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Classification Calibration for Long-tail Instance SegmentationCode1
CISCA and CytoDArk0: a Cell Instance Segmentation and Classification method for histo(patho)logical image Analyses and a new, open, Nissl-stained dataset for brain cytoarchitecture studiesCode1
4D Unsupervised Object DiscoveryCode1
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic SurgeryCode1
Classifying Breast Histopathology Images with a Ductal Instance-Oriented PipelineCode1
Detect, consolidate, delineate: scalable mapping of field boundaries using satellite imagesCode1
CEDNet: A Cascade Encoder-Decoder Network for Dense PredictionCode1
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale AmbiguitiesCode1
CHEX: CHannel EXploration for CNN Model CompressionCode1
Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19Code1
Advanced Deep Networks for 3D Mitochondria Instance SegmentationCode1
CenterMask: Real-Time Anchor-Free Instance SegmentationCode1
CenterPoly: real-time instance segmentation using bounding polygonsCode1
A Deep Learning Approach to Teeth Segmentation and Orientation from Panoramic X-raysCode1
CentripetalNet: Pursuing High-quality Keypoint Pairs for Object DetectionCode1
Depth-aware Object Segmentation and Grasp Detection for Robotic Picking TasksCode1
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small DatasetsCode1
Delving Deeper into Anti-aliasing in ConvNetsCode1
DenseCLIP: Language-Guided Dense Prediction with Context-Aware PromptingCode1
CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking DetectionCode1
CenterMask : Real-Time Anchor-Free Instance SegmentationCode1
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak SupervisionCode1
Show:102550
← PrevPage 4 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