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 12011225 of 2262 papers

TitleStatusHype
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition0
Tooth Instance Segmentation on Panoramic Dental Radiographs Using U-Nets and Morphological ProcessingCode1
Human Instance Segmentation and Tracking via Data Association and Single-stage Detector0
Exploring Plain Vision Transformer Backbones for Object DetectionCode2
CHEX: CHannel EXploration for CNN Model CompressionCode1
Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene SegmentationCode2
Self-Supervised Image Representation Learning with Geometric Set Consistency0
mc-BEiT: Multi-choice Discretization for Image BERT Pre-trainingCode1
Eigencontours: Novel Contour Descriptors Based on Low-Rank ApproximationCode1
SepViT: Separable Vision TransformerCode1
MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation0
HUNIS: High-Performance Unsupervised Nuclei Instance Segmentation0
Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?Code1
Semi-supervised machine learning model for analysis of nanowire morphologies from transmission electron microscopy imagesCode0
SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation0
Sparse Instance Activation for Real-Time Instance SegmentationCode2
Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention TransformerCode1
PaCa-ViT: Learning Patch-to-Cluster Attention in Vision TransformersCode1
Test-time Adaptation with Slot-Centric ModelsCode1
ContrastMask: Contrastive Learning to Segment Every ThingCode1
Object discovery and representation networksCode0
InsCon:Instance Consistency Feature Representation via Self-Supervised Learning0
Contrastive Learning for Automotive mmWave Radar Detection Points Based Instance Segmentation0
Deformable VisTR: Spatio temporal deformable attention for video instance segmentationCode0
One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-outCode0
Show:102550
← PrevPage 49 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