Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

2023/03/26 by Bohao Peng, Peng, Bohao, Zhuotao Tian +11 · 13 citations
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2303.14652

openalex publication_date 2023/03/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA
• DistillFSS: Synthesizing Few-Shot Knowledge into a Lightweight Segmentation Model
• Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-Free Open-Vocabulary Semantic Segmentation
• Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
• Omni-Referring Image Segmentation
• Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design
• Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentation
• Multi-Text Guided Few-Shot Semantic Segmentation
• Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentation
• FS-SAM2: Adapting Segment Anything Model 2 for Few-Shot Semantic Segmentation via Low-Rank Adaptation
• Object-level Correlation for Few-Shot Segmentation
• Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild
• Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation

Related

• Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract
• Object-level Correlation for Few-Shot Segmentation
• Hypercorrelation Squeeze for Few-Shot Segmentation
• Multi-similarity based Hyperrelation Network for few-shot segmentation
• Self-Support Few-Shot Semantic Segmentation