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 18761900 of 2262 papers

TitleStatusHype
LevelSet R-CNN: A Deep Variational Method for Instance Segmentation0
Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds0
Instance-aware Self-supervised Learning for Nuclei Segmentation0
Darwin's Neural Network: AI-based Strategies for Rapid and Scalable Cell and Coronavirus Screening0
Split and Expand: An inference-time improvement for Weakly Supervised Cell Instance Segmentation0
Can we cover navigational perception needs of the visually impaired by panoptic segmentation?0
Feature Pyramid Transformer0
Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances0
CASNet: Common Attribute Support Network for image instance and panoptic segmentation0
PerMO: Perceiving More at Once from a Single Image for Autonomous Driving0
TrashCan: A Semantically-Segmented Dataset towards Visual Detection of Marine Debris0
Unsupervised Spatio-temporal Latent Feature Clustering for Multiple-object Tracking and SegmentationCode0
Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation0
Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-SegmentCode0
Unsupervised object-centric video generation and decomposition in 3DCode0
Scalable, Proposal-free Instance Segmentation Network for 3D Pixel Clustering and Particle Trajectory Reconstruction in Liquid Argon Time Projection Chambers0
Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition0
A Survey on Instance Segmentation: State of the art0
SASO: Joint 3D Semantic-Instance Segmentation via Multi-scale Semantic Association and Salient Point Clustering Optimization0
NINEPINS: Nuclei Instance Segmentation with Point Annotations0
LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB0
Geometry-Aware Instance Segmentation with Disparity MapsCode0
Instance segmentation of buildings using keypoints0
Density-Based Clustering for 3D Object Detection in Point Clouds0
Video Instance Segmentation Tracking With a Modified VAE Architecture0
Show:102550
← PrevPage 76 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