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 726750 of 2262 papers

TitleStatusHype
Evolving Normalization-Activation LayersCode1
Balanced Meta-Softmax for Long-Tailed Visual RecognitionCode1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningCode1
PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB ImageCode1
Low Latency Instance Segmentation by Continuous Clustering for LiDAR SensorsCode1
A Review of Panoptic Segmentation for Mobile Mapping Point CloudsCode1
Long-tailed Instance Segmentation using Gumbel Optimized LossCode1
FcaNet: Frequency Channel Attention NetworksCode1
Exploring Classification Equilibrium in Long-Tailed Object DetectionCode1
All in Tokens: Unifying Output Space of Visual Tasks via Soft TokenCode1
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene ContextsCode1
PointGroup: Dual-Set Point Grouping for 3D Instance SegmentationCode1
A Robust Feature Downsampling Module for Remote Sensing Visual TasksCode1
Making Vision Transformers Efficient from A Token Sparsification ViewCode1
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-EncodersCode1
CenterMask : Real-Time Anchor-Free Instance SegmentationCode1
M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout AnalysisCode1
PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item DetectionCode1
CenterMask: Real-Time Anchor-Free Instance SegmentationCode1
Decoupling Classifier for Boosting Few-shot Object Detection and Instance SegmentationCode1
Efficient Attention: Attention with Linear ComplexitiesCode1
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular CamerasCode1
Mask Transfiner for High-Quality Instance SegmentationCode1
FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance SegmentationCode1
Plane Geometry Diagram ParsingCode1
Show:102550
← PrevPage 30 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