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 351375 of 2262 papers

TitleStatusHype
BoxSnake: Polygonal Instance Segmentation with Box SupervisionCode1
3D Mitochondria Instance Segmentation with Spatio-Temporal TransformersCode1
Making Vision Transformers Efficient from A Token Sparsification ViewCode1
DynaMask: Dynamic Mask Selection for Instance SegmentationCode1
SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance SegmentationCode1
Three Guidelines You Should Know for Universally Slimmable Self-Supervised LearningCode1
Amodal Intra-class Instance Segmentation: Synthetic Datasets and BenchmarkCode1
SEMv2: Table Separation Line Detection Based on Instance SegmentationCode1
ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR DataCode1
Traffic Scene Parsing through the TSP6K DatasetCode1
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic ConvolutionCode1
Kartezio: Evolutionary Design of Explainable Pipelines for Biomedical Image AnalysisCode1
Video-SwinUNet: Spatio-temporal Deep Learning Framework for VFSS Instance SegmentationCode1
CEDNet: A Cascade Encoder-Decoder Network for Dense PredictionCode1
Cross-Layer Retrospective Retrieving via Layer AttentionCode1
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot InteractionCode1
DilateFormer: Multi-Scale Dilated Transformer for Visual RecognitionCode1
ParticleSeg3D: A Scalable Out-of-the-Box Deep Learning Segmentation Solution for Individual Particle Characterization from Micro CT Images in Mineral Processing and RecyclingCode1
Long-tail Detection with Effective Class-MarginsCode1
Recurrent Generic Contour-based Instance Segmentation with Progressive LearningCode1
TarViS: A Unified Approach for Target-based Video SegmentationCode1
The CropAndWeed Dataset: A Multi-Modal Learning Approach for Efficient Crop and Weed ManipulationCode1
All in Tokens: Unifying Output Space of Visual Tasks via Soft TokenCode1
Reference Twice: A Simple and Unified Baseline for Few-Shot Instance SegmentationCode1
Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance SegmentationCode1
Show:102550
← PrevPage 15 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