TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/DHR: Dual Features-Driven Hierarchical Rebalancing in Inte...

DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation

Sanghyun Jo, Fei Pan, In-Jae Yu, KyungSu Kim

2024-03-30Weakly-Supervised Semantic SegmentationWeakly supervised Semantic SegmentationSegmentationSemantic Segmentation
PaperPDFCode(official)

Abstract

Weakly-supervised semantic segmentation (WSS) ensures high-quality segmentation with limited data and excels when employed as input seed masks for large-scale vision models such as Segment Anything. However, WSS faces challenges related to minor classes since those are overlooked in images with adjacent multiple classes, a limitation originating from the overfitting of traditional expansion methods like Random Walk. We first address this by employing unsupervised and weakly-supervised feature maps instead of conventional methodologies, allowing for hierarchical mask enhancement. This method distinctly categorizes higher-level classes and subsequently separates their associated lower-level classes, ensuring all classes are correctly restored in the mask without losing minor ones. Our approach, validated through extensive experimentation, significantly improves WSS across five benchmarks (VOC: 79.8\%, COCO: 53.9\%, Context: 49.0\%, ADE: 32.9\%, Stuff: 37.4\%), reducing the gap with fully supervised methods by over 84\% on the VOC validation set. Code is available at https://github.com/shjo-april/DHR.

Results

TaskDatasetMetricValueModel
Semantic SegmentationCOCO 2014 valmIoU56.8DHR (Swin-L, Mask2Former)
Semantic SegmentationCOCO-Stuff valmIoU37.4DHR (Swin-L, Mask2Former)
Semantic SegmentationPASCAL VOC 2012 valMean IoU82.3DHR (Swin-L, Mask2Former)
Semantic SegmentationPASCAL Context valmIoU53.6DHR (Swin-L, Mask2Former)
Semantic SegmentationPASCAL VOC 2012 testMean IoU82.3DHR (Swin-L, Mask2Former)
Semantic SegmentationADE20K valmIoU32.9DHR (Swin-L, Mask2Former)
10-shot image generationCOCO 2014 valmIoU56.8DHR (Swin-L, Mask2Former)
10-shot image generationCOCO-Stuff valmIoU37.4DHR (Swin-L, Mask2Former)
10-shot image generationPASCAL VOC 2012 valMean IoU82.3DHR (Swin-L, Mask2Former)
10-shot image generationPASCAL Context valmIoU53.6DHR (Swin-L, Mask2Former)
10-shot image generationPASCAL VOC 2012 testMean IoU82.3DHR (Swin-L, Mask2Former)
10-shot image generationADE20K valmIoU32.9DHR (Swin-L, Mask2Former)

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17