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/Hierarchical Dense Correlation Distillation for Few-Shot S...

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chenyao Wang, Shu Liu, Jingyong Su, Jiaya Jia

2023-03-26CVPR 2023 1Semantic correspondenceSegmentationFew-Shot Semantic SegmentationSemantic Segmentation
PaperPDFCode(official)

Abstract

Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve $50.0\%$ mIoU on \coco~dataset one-shot setting and $56.0\%$ on five-shot segmentation, respectively.

Results

TaskDatasetMetricValueModel
Few-Shot LearningCOCO-20i (5-shot)FB-IoU77.7HDMNet (ResNet-50)
Few-Shot LearningCOCO-20i (5-shot)Mean IoU56HDMNet (ResNet-50)
Few-Shot LearningCOCO-20i (5-shot)Mean IoU52.4HDMNet (VGG-16)
Few-Shot LearningPASCAL-5i (1-Shot)Mean IoU69.4HDMNet (ResNet-50)
Few-Shot LearningPASCAL-5i (1-Shot)Mean IoU65.1HDMNet (VGG-16)
Few-Shot LearningCOCO-20i (1-shot)FB-IoU72.2HDMNet (ResNet-50)
Few-Shot LearningCOCO-20i (1-shot)Mean IoU50HDMNet (ResNet-50)
Few-Shot LearningCOCO-20i (1-shot)Mean IoU45.9HDMNet (VGG-16)
Few-Shot LearningPASCAL-5i (5-Shot)Mean IoU71.8HDMNet (ResNet-50)
Few-Shot LearningPASCAL-5i (5-Shot)Mean IoU69.3HDMNet (VGG-16)
Few-Shot Semantic SegmentationCOCO-20i (5-shot)FB-IoU77.7HDMNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (5-shot)Mean IoU56HDMNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (5-shot)Mean IoU52.4HDMNet (VGG-16)
Few-Shot Semantic SegmentationPASCAL-5i (1-Shot)Mean IoU69.4HDMNet (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (1-Shot)Mean IoU65.1HDMNet (VGG-16)
Few-Shot Semantic SegmentationCOCO-20i (1-shot)FB-IoU72.2HDMNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (1-shot)Mean IoU50HDMNet (ResNet-50)
Few-Shot Semantic SegmentationCOCO-20i (1-shot)Mean IoU45.9HDMNet (VGG-16)
Few-Shot Semantic SegmentationPASCAL-5i (5-Shot)Mean IoU71.8HDMNet (ResNet-50)
Few-Shot Semantic SegmentationPASCAL-5i (5-Shot)Mean IoU69.3HDMNet (VGG-16)
Meta-LearningCOCO-20i (5-shot)FB-IoU77.7HDMNet (ResNet-50)
Meta-LearningCOCO-20i (5-shot)Mean IoU56HDMNet (ResNet-50)
Meta-LearningCOCO-20i (5-shot)Mean IoU52.4HDMNet (VGG-16)
Meta-LearningPASCAL-5i (1-Shot)Mean IoU69.4HDMNet (ResNet-50)
Meta-LearningPASCAL-5i (1-Shot)Mean IoU65.1HDMNet (VGG-16)
Meta-LearningCOCO-20i (1-shot)FB-IoU72.2HDMNet (ResNet-50)
Meta-LearningCOCO-20i (1-shot)Mean IoU50HDMNet (ResNet-50)
Meta-LearningCOCO-20i (1-shot)Mean IoU45.9HDMNet (VGG-16)
Meta-LearningPASCAL-5i (5-Shot)Mean IoU71.8HDMNet (ResNet-50)
Meta-LearningPASCAL-5i (5-Shot)Mean IoU69.3HDMNet (VGG-16)

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