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 551600 of 2262 papers

TitleStatusHype
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo LabelersCode1
DocSegTr: An Instance-Level End-to-End Document Image Segmentation TransformerCode1
Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater EnvironmentCode1
3D Indoor Instance Segmentation in an Open-WorldCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality AnnotationsCode1
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningCode1
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise BinarizationCode1
GAInS: Gradient Anomaly-aware Biomedical Instance SegmentationCode1
3D Instances as 1D KernelsCode1
Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance SegmentationCode1
Test-time Adaptation with Slot-Centric ModelsCode1
GradAug: A New Regularization Method for Deep Neural NetworksCode1
Amodal Intra-class Instance Segmentation: Synthetic Datasets and BenchmarkCode1
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point CloudCode1
Human Instance Matting via Mutual Guidance and Multi-Instance RefinementCode1
Delving Deeper into Anti-aliasing in ConvNetsCode1
DenseCLIP: Language-Guided Dense Prediction with Context-Aware PromptingCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2Code1
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance SegmentationCode1
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANsCode1
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-RefinementCode1
Depth-aware Object Segmentation and Grasp Detection for Robotic Picking TasksCode1
FourierNet: Compact mask representation for instance segmentation using differentiable shape decodersCode1
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small DatasetsCode1
iBOT: Image BERT Pre-Training with Online TokenizerCode1
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance SegmentationCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
Implicit Feature Refinement for Instance SegmentationCode1
Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point CloudsCode1
Detect, consolidate, delineate: scalable mapping of field boundaries using satellite imagesCode1
FsaNet: Frequency Self-attention for Semantic SegmentationCode1
Deep Learning based Food Instance Segmentation using Synthetic DataCode1
Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19Code1
Inception Convolution with Efficient Dilation SearchCode1
Indoor Panorama Planar 3D Reconstruction via Divide and ConquerCode1
Focal Self-attention for Local-Global Interactions in Vision TransformersCode1
FinnWoodlands DatasetCode1
Instance As Identity: A Generic Online Paradigm for Video Instance SegmentationCode1
Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data AugmentationCode1
FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous DrivingCode1
FoodSAM: Any Food SegmentationCode1
DeVIS: Making Deformable Transformers Work for Video Instance SegmentationCode1
DFormer: Diffusion-guided Transformer for Universal Image SegmentationCode1
Fully Automated Scan-to-BIM Via Point Cloud Instance SegmentationCode1
Deep learning approaches to building rooftop thermal bridge detection from aerial imagesCode1
BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online PoliciesCode1
DilateFormer: Multi-Scale Dilated Transformer for Visual RecognitionCode1
FcaNet: Frequency Channel Attention NetworksCode1
Show:102550
← PrevPage 12 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