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 926950 of 2262 papers

TitleStatusHype
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground TruthCode0
Precise Location Matching Improves Dense Contrastive Learning in Digital PathologyCode0
Prohibited Items Segmentation via Occlusion-aware Bilayer ModelingCode0
Gated Channel Transformation for Visual RecognitionCode0
Assessment of Cell Nuclei AI Foundation Models in Kidney PathologyCode0
Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic ModelCode0
PM-VIS+: High-Performance Video Instance Segmentation without Video AnnotationCode0
From Seedling to Harvest: The GrowingSoy Dataset for Weed Detection in Soy Crops via Instance SegmentationCode0
ClusterFuG: Clustering Fully connected Graphs by MulticutCode0
3D-SIS: 3D Semantic Instance Segmentation of RGB-D ScansCode0
Point Cloud Instance Segmentation with Semi-supervised Bounding-Box MiningCode0
PolyTransform: Deep Polygon Transformer for Instance SegmentationCode0
Prompting Vision-Language Model for Nuclei Instance Segmentation and ClassificationCode0
SEINE: Structure Encoding and Interaction Network for Nuclei Instance SegmentationCode0
From Density to Geometry: YOLOv8 Instance Segmentation for Reverse Engineering of Optimized StructuresCode0
Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower SpeciesCode0
Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive ArchitectureCode0
FrGNet: A fourier-guided weakly-supervised framework for nuclear instance segmentationCode0
A 3D Convolutional Approach to Spectral Object Segmentation in Space and TimeCode0
PixelLink: Detecting Scene Text via Instance SegmentationCode0
Pixelwise Instance Segmentation with a Dynamically Instantiated NetworkCode0
A Spacecraft Dataset for Detection, Segmentation and Parts RecognitionCode0
Fractal Calibration for long-tailed object detectionCode0
A Dataset for Analysing Complex Document Layouts in the Digital Humanities and Its Evaluation with Krippendorff’s AlphaCode0
Pixel-Level Analysis for Enhancing Threat Detection in Large-Scale X-ray Security ImagesCode0
Show:102550
← PrevPage 38 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