Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervals

2025/09/01 by Huan Ni, Ni, Huan, Qingshan Liu +9
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Fault Diagnosis Techniques

paper · pdf · doi:10.48550/arxiv.2509.01299

openalex publication_date 2025/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Cross-domain few-shot segmentation (CD-FSS) aims to segment unseen categories with very limited samples while alleviating the negative effects of domain shift between the source and target domains. At present, existing CD-FSS studies typically rely on multiple independent modules to enhance cross-domain adaptability. However, the independence among these modules hinders the effective flow of knowledge, making it difficult to fully leverage their collective potential. In contrast, this paper proposes an all-in-one module based on ordinary differential equations (ODEs) and the Fourier transform, resulting in a structurally concise method-Few-Shot Segmentation over Time Intervals (FSS-TIs). FSS-TIs not only explores a domain-agnostic feature space, but also achieves significant performance improvement through target-domain fine-tuning with extremely limited support samples. Specifically, the ODE modeling process incorporates nonlinear transformations and random perturbations of the amplitude and phase spectra, effectively simulating potential target-domain data distributions. Meanwhile, the analytical solution of the ODE is transformed into a theoretically infinitely iterable feature refinement process, thereby enhancing the learning capability under limited support samples. In this way, both the exploration of domain-agnostic features and the few-shot learning problem can be addressed through the optimization of the intrinsic parameters of the ODE. Moreover, during target-domain fine-tuning, we strictly constrain the support samples to match the settings of real-world CD-FSS tasks, without incurring additional annotation costs. Experimental results demonstrate the superiority of FSS-TIs over existing CD-FSS methods, and in-depth ablation studies further validate the cross-domain adaptability of FSS-TIs.

Citations

• Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
• Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
• The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
• DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
• Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
• Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentation
• APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation
• Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation
• Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation
• Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation
• Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining
• SpectralGPT: Spectral Remote Sensing Foundation Model
• RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Network
• Self-Calibrated Cross Attention Network for Few-Shot Segmentation
• Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation
• Micrograph segmentations for DDEVD
• Segment Anything
• Cross-domain Few-shot Segmentation with Transductive Fine-tuning
• Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
• Self-Support Few-Shot Semantic Segmentation
• Learning Non-target Knowledge for Few-shot Semantic Segmentation
• LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
• PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
• Few-Shot Segmentation via Cycle-Consistent Transformer
• Diffusion Mechanism in Residual Neural Network: Theory and Applications
• Hypercorrelation Squeeze for Few-Shot Segmentation
• Prototype Mixture Models for Few-shot Semantic Segmentation
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• Part-aware Prototype Network for Few-shot Semantic Segmentation
• FDA: Fourier Domain Adaptation for Semantic Segmentation
• CRNet: Cross-Reference Networks for Few-Shot Segmentation
• Feature Weighting and Boosting for Few-Shot Segmentation
• PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
• iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
• Neural Ordinary Differential Equations
• Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
• One-Shot Learning for Semantic Segmentation
• The Reversible Residual Network: Backpropagation Without Storing Activations
• PolyNet: A Pursuit of Structural Diversity in Very Deep Networks
• FractalNet: Ultra-Deep Neural Networks without Residuals
• Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017\n International Symposium on Biomedical Imaging (ISBI), Hosted by the\n International Skin Imaging Collaboration (ISIC)
• Deep Residual Learning for Image Recognition

Related

• Cross-domain Few-shot Segmentation with Transductive Fine-tuning
• Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation
• DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptation
• The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
• Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation