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 20012050 of 2262 papers

TitleStatusHype
Is Heuristic Sampling Necessary in Training Deep Object Detectors?Code0
Fast Scene Understanding for Autonomous DrivingCode0
Union-over-Intersections: Object Detection beyond Winner-Takes-AllCode0
Pose2Seg: Detection Free Human Instance SegmentationCode0
PolyTransform: Deep Polygon Transformer for Instance SegmentationCode0
Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic ModelCode0
Point Cloud Instance Segmentation with Semi-supervised Bounding-Box MiningCode0
An interpretable automated detection system for FISH-based HER2 oncogene amplification testing in histo-pathological routine images of breast and gastric cancer diagnosticsCode0
PM-VIS+: High-Performance Video Instance Segmentation without Video AnnotationCode0
CellTrack R-CNN: A Novel End-To-End Deep Neural Network for Cell Segmentation and Tracking in Microscopy ImagesCode0
Faster Training of Mask R-CNN by Focusing on Instance BoundariesCode0
Pixelwise Instance Segmentation with a Dynamically Instantiated NetworkCode0
Cell tracking for live-cell microscopy using an activity-prioritized assignment strategyCode0
PixelLink: Detecting Scene Text via Instance SegmentationCode0
The Projection-Enhancement Network (PEN)Code0
Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNNCode0
CCNet: Criss-Cross Attention for Semantic SegmentationCode0
Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security ImagesCode0
Robot Instance Segmentation with Few Annotations for GraspingCode0
Robust 2D/3D Vehicle Parsing in Arbitrary Camera Views for CVISCode0
Fashion-Guided Adversarial Attack on Person SegmentationCode0
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding ModelCode0
CBNet: A Novel Composite Backbone Network Architecture for Object DetectionCode0
An expert-driven data generation pipeline for histological imagesCode0
Robust Approximate Characterization of Single-Cell Heterogeneity in Microbial GrowthCode0
Medical Image Fusion for High-Level Analysis: A Mutual Enhancement Framework for Unaligned PAT and MRICode0
The Second-place Solution for CVPR VISION 23 Challenge Track 1 -- Data Effificient Defect DetectionCode0
Video Instance Segmentation in an Open-WorldCode0
Robust Online Video Instance Segmentation with Track QueriesCode0
Robust Perception through EquivarianceCode0
Accurate Fine-grained Layout Analysis for the Historical Tibetan Document Based on the Instance SegmentationCode0
PatchDCT: Patch Refinement for High Quality Instance SegmentationCode0
The surprising impact of mask-head architecture on novel class segmentationCode0
PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object UnderstandingCode0
False Negative Reduction in Video Instance Segmentation using Uncertainty EstimatesCode0
Partial-Attribution Instance Segmentation for Astronomical Source Detection and DeblendingCode0
PanoSLAM: Panoptic 3D Scene Reconstruction via Gaussian SLAMCode0
Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually ImpairedCode0
Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point SupervisionCode0
ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of ThoughtsCode0
Exploring Target Representations for Masked AutoencodersCode0
S4Net: Single Stage Salient-Instance SegmentationCode0
SA3DIP: Segment Any 3D Instance with Potential 3D PriorsCode0
Cascade R-CNN: High Quality Object Detection and Instance SegmentationCode0
Exploiting Depth Information for Wildlife MonitoringCode0
Explicit Shape Encoding for Real-Time Instance SegmentationCode0
EVA: Exploring the Limits of Masked Visual Representation Learning at ScaleCode0
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic SegmentationCode0
CARAFE: Content-Aware ReAssembly of FEaturesCode0
EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational DataCode0
Show:102550
← PrevPage 41 of 46Next →

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