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 526550 of 2262 papers

TitleStatusHype
CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking DetectionCode1
UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place SolutionCode1
Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer AggregationCode1
PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB ImageCode1
Mask-aware IoU for Anchor Assignment in Real-time Instance SegmentationCode1
1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021Code1
The Aircraft Context Dataset: Understanding and Optimizing Data Variability in Aerial DomainsCode1
Long-tailed Distribution AdaptationCode1
Clustering Plotted Data by Image SegmentationCode1
Transformer Assisted Convolutional Network for Cell Instance SegmentationCode1
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk ControlCode1
Instance Segmentation Challenge Track Technical Report, VIPriors Workshop at ICCV 2021: Task-Specific Copy-Paste Data Augmentation Method for Instance SegmentationCode1
Deep Structured Instance Graph for Distilling Object DetectorsCode1
Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion ModelingCode1
LGD: Label-guided Self-distillation for Object DetectionCode1
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-RefinementCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with TransformersCode1
RAMA: A Rapid Multicut Algorithm on GPUCode1
LIVECell—A large-scale dataset for label-free live cell segmentationCode1
A Weakly Supervised Amodal Segmenter with Boundary Uncertainty EstimationCode1
BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online PoliciesCode1
CenterPoly: real-time instance segmentation using bounding polygonsCode1
Exploring Classification Equilibrium in Long-Tailed Object DetectionCode1
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree NetworksCode1
Show:102550
← PrevPage 22 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