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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2101–2150 of 2262 papers

TitleStatusHype
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point CloudCode1
Scale-aware multi-level guidance for interactive instance segmentation—0
PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object UnderstandingCode0
Learning to Fuse Things and Stuff—0
Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics—0
Efficient Attention: Attention with Linear ComplexitiesCode1
Beyond Grids: Learning Graph Representations for Visual Recognition—0
TextMountain: Accurate Scene Text Detection via Instance Segmentation—0
One-Shot Instance SegmentationCode1
CCNet: Criss-Cross Attention for Semantic SegmentationCode0
Deformable ConvNets v2: More Deformable, Better ResultsCode1
Affinity Derivation and Graph Merge for Instance SegmentationCode0
GANtruth - an unpaired image-to-image translation method for driving scenarios—0
Non-local RoI for Cross-Object Perception—0
A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation—0
A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization—0
Rethinking ImageNet Pre-training—0
Scene Text Detection with Supervised Pyramid Context NetworkCode0
Slum Segmentation and Change Detection : A Deep Learning ApproachCode0
Domain Randomization for Scene-Specific Car Detection and Pose EstimationCode0
Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNNCode0
Learning Segmentation Masks with the Independence Prior—0
Deep Semantic Instance Segmentation of Tree-like Structures Using Synthetic Data—0
Rain Removal in Traffic Surveillance: Does it Matter?Code0
Mask Propagation Network for Video Object Segmentation—0
Investigating Object Compositionality in Generative Adversarial Networks—0
CNN-based Preprocessing to Optimize Watershed-based Cell Segmentation in 3D Confocal Microscopy Images—0
BshapeNet: Object Detection and Instance Segmentation with Bounding Shape Masks—0
Multi-Task Learning as Multi-Objective OptimizationCode2
Artistic Instance-Aware Image Filtering by Convolutional Neural Networks—0
Faster Training of Mask R-CNN by Focusing on Instance BoundariesCode0
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic DataCode0
Robust Adversarial Perturbation on Deep Proposal-based Models—0
Geometric Image Synthesis—0
Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information—0
Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network—0
On the Importance of Visual Context for Data Augmentation in Scene Understanding—0
WildDash - Creating Hazard-Aware Benchmarks—0
DetNet: Design Backbone for Object Detection—0
Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation—0
Weakly- and Semi-Supervised Panoptic SegmentationCode1
Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning—0
Traits & Transferability of Adversarial Examples against Instance Segmentation & Object Detection—0
Deep Leaf Segmentation Using Synthetic DataCode0
Semi-convolutional Operators for Instance Segmentation—0
Instance Segmentation by Deep ColoringCode0
ClusterNet: 3D Instance Segmentation in RGB-D Images—0
Actor-Action Semantic Segmentation with Region Masks—0
Bounding Box Embedding for Single Shot Person Instance Segmentation—0
Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation—0
Show:102550
← PrevPage 43 of 46Next →
All datasetsCOCO test-devCOCO minivalLVIS v1.0 valCityscapes valADE20K valARMBenchOccluded COCOOoDISSeparated COCOTBBRBDD100K valCOCO val (panoptic labels)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-HAP5080.8—Unverified
2ResNeSt-200 (multi-scale)AP5070.2—Unverified
3CenterMask + VoVNetV2-99 (multi-scale)AP5066.2—Unverified
4CenterMask + VoVNetV2-57 (single-scale)AP5060.8—Unverified
5Co-DETRmask AP57.1—Unverified
6CBNetV2 (EVA02, single-scale)mask AP56.1—Unverified
7ISDA (ResNet-50)APL55.7—Unverified
8EVAmask AP55.5—Unverified
9FD-SwinV2-Gmask AP55.4—Unverified
10Mask Frozen-DETRmask AP55.3—Unverified
#ModelMetricClaimedVerifiedStatus
1InternImage-BGFLOPs501—Unverified
2Co-DETRmask AP56.6—Unverified
3ViT-CoMer-L (Mask RCNN, DINOv2)mask AP55.9—Unverified
4InternImage-Hmask AP55.4—Unverified
5EVAmask AP55—Unverified
6Mask Frozen-DETRmask AP54.9—Unverified
7MasK DINO (SwinL, multi-scale)mask AP54.5—Unverified
8ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)mask AP54.2—Unverified
9GLEE-Promask AP54.2—Unverified
10SwinV2-G (HTC++)mask AP53.7—Unverified