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 326350 of 2262 papers

TitleStatusHype
DoNet: Deep De-overlapping Network for Cytology Instance SegmentationCode1
Active Pointly-Supervised Instance SegmentationCode1
CenterPoly: real-time instance segmentation using bounding polygonsCode1
DropLoss for Long-Tail Instance SegmentationCode1
DVIS: Decoupled Video Instance Segmentation FrameworkCode1
A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection from Aerial ImagesCode1
DynaMask: Dynamic Mask Selection for Instance SegmentationCode1
Detect, consolidate, delineate: scalable mapping of field boundaries using satellite imagesCode1
Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19Code1
3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance SegmentationCode1
CEDNet: A Cascade Encoder-Decoder Network for Dense PredictionCode1
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small DatasetsCode1
Cached Transformers: Improving Transformers with Differentiable Memory CacheCode1
DeVIS: Making Deformable Transformers Work for Video Instance SegmentationCode1
CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance SegmentationCode1
Efficient Self-supervised Vision Pretraining with Local Masked ReconstructionCode1
Delving Deeper into Anti-aliasing in ConvNetsCode1
Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor SceneCode1
A One Stop 3D Target Reconstruction and multilevel Segmentation MethodCode1
Embedding-based Instance Segmentation in MicroscopyCode1
DenseCLIP: Language-Guided Dense Prediction with Context-Aware PromptingCode1
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm QuantizerCode1
End-to-End Referring Video Object Segmentation with Multimodal TransformersCode1
Applying Eigencontours to PolarMask-Based Instance SegmentationCode1
Deep Variational Instance SegmentationCode1
Show:102550
← PrevPage 14 of 91Next →

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