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 19512000 of 2262 papers

TitleStatusHype
BlenderProcCode2
Learning to Track Any Object0
Team PFDet's Methods for Open Images Challenge 20190
Identifying Unknown Instances for Autonomous Driving0
SpatialFlow: Bridging All Tasks for Panoptic SegmentationCode1
Organ At Risk Segmentation with Multiple Modality0
What's in my Room? Object Recognition on Indoor Panoramic Images0
Panoptic-DeepLabCode0
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation0
Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods0
Multi-view PointNet for 3D Scene Understanding0
LIP: Learning Instance Propagation for Video Object Segmentation0
End-to-End Deep Convolutional Active Contours for Image Segmentation0
Salient Instance Segmentation via Subitizing and Clustering0
PolarMask: Single Shot Instance Segmentation with Polar RepresentationCode1
Geomorphological Analysis Using Unpiloted Aircraft Systems, Structure from Motion, and Deep Learning0
Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds0
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and ResolutionCode1
Multi-Task Learning via Scale Aware Feature Pyramid Networks and Effective Joint Head0
A closer look at network resolution for efficient network design0
Rescan: Inductive Instance Segmentation for Indoor RGBD Scans0
Gated Channel Transformation for Visual RecognitionCode0
AdaptIS: Adaptive Instance Selection NetworkCode0
Global Aggregation then Local Distribution in Fully Convolutional NetworksCode1
Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices0
Center-Extraction-Based Three Dimensional Nuclei Instance Segmentation of Fluorescence Microscopy Images0
Is Heuristic Sampling Necessary in Training Deep Object Detectors?Code0
BERTgrid: Contextualized Embedding for 2D Document Representation and UnderstandingCode0
Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation0
CBNet: A Novel Composite Backbone Network Architecture for Object DetectionCode0
NuClick: From Clicks in the Nuclei to Nuclear Boundaries0
SSAP: Single-Shot Instance Segmentation With Affinity PyramidCode0
Nuclear Instance Segmentation using a Proposal-Free Spatially Aware Deep Learning Framework0
A Weakly Supervised Method for Instance Segmentation of Biological Cells0
Generator evaluator-selector net for panoptic image segmentation and splitting unfamiliar objects into partsCode0
Towards Unconstrained End-to-End Text Spotting0
DISCo: Deep learning, Instance Segmentation, and Correlations for cell segmentation in calcium imagingCode0
InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-PastingCode0
Deep High-Resolution Representation Learning for Visual RecognitionCode1
Instance Scale Normalization for image understanding0
IRNet: Instance Relation Network for Overlapping Cervical Cell SegmentationCode0
Explicit Shape Encoding for Real-Time Instance SegmentationCode0
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature FusionCode1
LVIS: A Dataset for Large Vocabulary Instance SegmentationCode1
Attentive NormalizationCode0
The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation0
Distill-to-Label: Weakly Supervised Instance Labeling Using Knowledge Distillation0
Grape detection, segmentation and tracking using deep neural networks and three-dimensional associationCode0
Object as Distribution0
Show:102550
← PrevPage 40 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