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 1451–1500 of 2262 papers

TitleStatusHype
Poly-NL: Linear Complexity Non-local Layers with Polynomials—0
Stateless actor-critic for instance segmentation with high-level priors—0
On Model Calibration for Long-Tailed Object Detection and Instance SegmentationCode1
What Makes for Hierarchical Vision Transformer?—0
CBNet: A Composite Backbone Network Architecture for Object DetectionCode1
Focal Self-attention for Local-Global Interactions in Vision TransformersCode1
Simple Training Strategies and Model Scaling for Object Detection—0
SOLO: A Simple Framework for Instance Segmentation—0
False Negative Reduction in Video Instance Segmentation using Uncertainty EstimatesCode0
K-Net: Towards Unified Image SegmentationCode1
Indoor Panorama Planar 3D Reconstruction via Divide and ConquerCode1
Descriptive Modeling of Textiles using FE Simulations and Deep Learning—0
All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection—0
Real-time Instance Segmentation with Discriminative Orientation MapsCode1
P2T: Pyramid Pooling Transformer for Scene UnderstandingCode1
Tracking Instances as QueriesCode1
VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning—0
SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving—0
A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation—0
LPSNet: A Lightweight Solution for Fast Panoptic Segmentation—0
Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation—0
ColorRL: Reinforced Coloring for End-to-End Instance Segmentation—0
Hierarchical Lovasz Embeddings for Proposal-Free Panoptic Segmentation—0
MSN: Efficient Online Mask Selection Network for Video Instance SegmentationCode0
A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation—0
How can we learn (more) from challenges? A statistical approach to driving future algorithm development—0
XCiT: Cross-Covariance Image TransformersCode3
End-to-End Semi-Supervised Object Detection with Soft TeacherCode1
A Spacecraft Dataset for Detection, Segmentation and Parts RecognitionCode0
Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological ImagesCode1
DMSANet: Dual Multi Scale Attention Network—0
Enforcing Morphological Information in Fully Convolutional Networks to Improve Cell Instance Segmentation in Fluorescence Microscopy ImagesCode0
Revisiting Contrastive Methods for Unsupervised Learning of Visual RepresentationsCode2
Salient Object Ranking with Position-Preserved AttentionCode1
Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation—0
Affinity Attention Graph Neural Network for Weakly Supervised Semantic SegmentationCode1
Video Instance Segmentation using Inter-Frame Communication TransformersCode1
Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation—0
ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass—0
supervised adptive threshold network for instance segmentation—0
SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video DecompositionCode0
Vision Transformers with Hierarchical AttentionCode1
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable ApproachCode1
Detect, consolidate, delineate: scalable mapping of field boundaries using satellite imagesCode1
X-volution: On the unification of convolution and self-attention—0
SOLQ: Segmenting Objects by Learning QueriesCode1
Container: Context Aggregation NetworkCode1
Dual-stream Network for Visual Recognition—0
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural NetworkCode1
Less is More: Pay Less Attention in Vision TransformersCode1
Show:102550
← PrevPage 30 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