# SVasP: Self-Versatility Adversarial Style Perturbation for Cross-Domain Few-Shot Learning

arXiv: https://arxiv.org/abs/2412.09073 · HTML: https://mlsanity.com/paper/2412.09073/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 58 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 6 of 6)

- [Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification](https://mlsanity.com/paper/2005.08463/) (2020)
- [WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models](https://mlsanity.com/paper/2406.17503/) (2024)
- [Transferring Core Knowledge via Learngenes](https://mlsanity.com/paper/2401.08139/) (2024)
- [KIND: Knowledge Integration and Diversion for Training Decomposable Models](https://mlsanity.com/paper/2408.07337/) (2024)
- [Genes in Intelligent Agents](https://mlsanity.com/paper/2306.10225/) (2023)
- [Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation](https://mlsanity.com/paper/2410.24160/) (2024)

## Built on by (most cited first, 5 of 5)

- [VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning](https://mlsanity.com/paper/2509.25033/) (2025)
- [DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning](https://mlsanity.com/paper/2602.00795/) (2026)
- [FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning](https://mlsanity.com/paper/2505.08349/) (2025)
- [IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learning](https://mlsanity.com/paper/2601.11669/) (2026)
- [SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2603.05135/) (2026)

## Abstract (arXiv)

Cross-Domain Few-Shot Learning (CD-FSL) aims to transfer knowledge from seen source domains to unseen target domains, which is crucial for evaluating the generalization and robustness of models. Recent studies focus on utilizing visual styles to bridge the domain gap between different domains. However, the serious dilemma of gradient instability and local optimization problem occurs in those style-based CD-FSL methods. This paper addresses these issues and proposes a novel crop-global style perturbation method, called underlineSelf-underlineVersatility underlineAdversarial underlineStyle underlinePerturbation (SVasP), which enhances the gradient stability and escapes from poor sharp minima jointly. Specifically, SVasP simulates more diverse potential target domain adversarial styles via diversifying input patterns and aggregating localized crop style gradients, to serve as global style perturbation stabilizers within one image, a concept we refer to as self-versatility. Then a novel objective function is proposed to maximize visual discrepancy while maintaining semantic consistency between global, crop, and adversarial features. Having the stabilized global style perturbation in the training phase, one can obtain a flattened minima in the loss landscape, boosting the transferability of the model to the target domains. Extensive experiments on multiple benchmark datasets demonstrate that our method significantly outperforms existing state-of-the-art methods. Our codes are available at https://github.com/liwenqianSEU/SVasP.