SOTAVerified

Semantic Segmentation

Papers

Showing 49765000 of 14763 papers

TitleStatusHype
MobileViG: Graph-Based Sparse Attention for Mobile Vision ApplicationsCode1
SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose EstimationCode1
SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency0
Obscured Wildfire Flame Detection By Temporal Analysis of Smoke Patterns Captured by Unmanned Aerial Systems0
Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic SegmentationCode1
Multiscale Progressive Text Prompt Network for Medical Image Segmentation0
Topological Data Analysis Guided Segment Anything Model Prompt Optimization for Zero-Shot Segmentation in Biological Imaging0
Achieving RGB-D level Segmentation Performance from a Single ToF Camera0
PCDAL: A Perturbation Consistency-Driven Active Learning Approach for Medical Image Segmentation and ClassificationCode0
The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One ShotCode4
MIS-FM: 3D Medical Image Segmentation using Foundation Models Pretrained on a Large-Scale Unannotated DatasetCode2
MLA-BIN: Model-level Attention and Batch-instance Style Normalization for Domain Generalization of Federated Learning on Medical Image Segmentation0
Learning Nuclei Representations with Masked Image Modelling0
M3Act: Learning from Synthetic Human Group Activities0
Inter-Rater Uncertainty Quantification in Medical Image Segmentation via Rater-Specific Bayesian Neural NetworksCode0
Analysis of LiDAR Configurations on Off-road Semantic Segmentation Performance0
SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar SegmentationCode1
RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation ModelCode2
Fast Marching Energy CNN0
Let Segment Anything Help Image Dehaze0
High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error RefinementCode1
Incremental Learning on Food Instance Segmentation0
Chan-Vese Attention U-Net: An attention mechanism for robust segmentation0
Land Cover Segmentation with Sparse Annotations from Sentinel-2 ImageryCode1
1M parameters are enough? A lightweight CNN-based model for medical image segmentationCode1
Show:102550
← PrevPage 200 of 591Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternImage-H (M3I Pre-training)Params (M)1,310Unverified
2ViT-P (InternImage-H)Validation mIoU63.6Unverified
3ONE-PEACEValidation mIoU63Unverified
4M3I Pre-training (InternImage-H)Validation mIoU62.9Unverified
5InternImage-HValidation mIoU62.9Unverified
6BEiT-3Validation mIoU62.8Unverified
7EVAValidation mIoU62.3Unverified
8ViT-P (OneFormer, InternImage-H)Validation mIoU61.6Unverified
9ViT-Adapter-L (Mask2Former, BEiTv2 pretrain)Validation mIoU61.5Unverified
10FD-SwinV2-GValidation mIoU61.4Unverified