用短程排斥机制防止表征坍缩，提升细粒度分类性能
Hypersolid: Emergent Vision Representations via Short-Range Repulsion
- 将表征学习视为离散堆积问题，用短程硬球排斥避免局部碰撞
- 在细粒度和低分辨率分类任务上表现优于现有方法
- 适合关注表征多样性与小样本分类的研究者
自监督学习中，表征坍缩是常见挑战。现有方法多依赖全局正则化，如最大化距离、解相关或强制分布。本文重新将表征学习视为离散堆积问题，保持信息完整性即维持单射性。提出Hypersolid方法，通过短程硬球排斥防止局部碰撞，形成高分离几何结构，有效保留增强多样性，在细粒度分类与低分辨率分类任务中表现优异。
原文摘要 · Abstract (English)
A recurring challenge in self-supervised learning is preventing representation collapse. Existing solutions typically rely on global regularization, such as maximizing distances, decorrelating dimensions or enforcing certain distributions. We instead reinterpret representation learning as a discrete packing problem, where preserving information simplifies to maintaining injectivity. We operationalize this in Hypersolid, a method using short-range hard-ball repulsion to prevent local collisions. This constraint results in a high-separation geometric regime that preserves augmentation diversity, excelling on fine-grained and low-resolution classification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。