解决分布式数据下的零样本视觉识别问题，提升未见类别识别效果。
Distributed Zero-Shot Learning for Visual Recognition
- 通过跨节点属性正则化稳定特征空间，促进跨节点语义对齐。
- 引入全局属性-视觉一致性机制，避免单点偏差导致的映射失真。
- 适用于数据分散、隐私敏感场景，适合联邦学习等分布式系统应用。
本文提出一种分布式零样本学习（DistZSL）框架，充分利用去中心化数据学习有效模型以识别未见类别。针对分布式节点间的数据异构性问题，引入两个关键组件：跨节点属性正则化和全局属性-视觉共识。跨节点属性正则化强制不同节点间属性特征距离保持一致，使整体属性特征空间在训练过程中保持稳定，从而促进视觉到属性（V2A）关系的建立。同时，全局属性-视觉共识通过约束各节点间属性与视觉特征分布的双向映射一致性，缓解单个节点学习带来的偏差。实验表明，DistZSL 在分布式数据上显著优于现有最优方法。
原文摘要 · Abstract (English)
In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we introduce two key components to ensure the effective learning of DistZSL: a cross-node attribute regularizer and a global attribute-to-visual consensus. Our proposed cross-node attribute regularizer enforces the distances between attribute features to be similar across different nodes. In this manner, the overall attribute feature space would be stable during learning, and thus facilitate the establishment of visual-to-attribute(V2A) relationships. Then, we introduce the global attribute-tovisual consensus to mitigate biased V2A mappings learned from individual nodes. Specifically, we enforce the bilateral mapping between the attribute and visual feature distributions to be consistent across different nodes. Thus, the learned consistent V2A mapping can significantly enhance zero-shot learning across different nodes. Extensive experiments demonstrate that DistZSL achieves superior performance to the state-of-the-art in learning from distributed data.
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。