Fine-grained categories that largely share the same set of parts cannot be discriminated based on part information alone, as they mostly differ in the way the local parts relate to the overall global structure of the object. We propose Relational Proxies, a novel approach that leverages the relational information between the global and local views of an object for encoding its semantic label. Starting with a rigorous formalization of the notion of distinguishability between fine-grained categories, we prove the necessary and sufficient conditions that a model must satisfy in order to learn the underlying decision boundaries in the fine-grained setting. We design Relational Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets and achieve state-of-the-art results on all of them, surpassing the performance of all existing works with a margin exceeding 4% in some cases. We also experimentally validate our theory on fine-grained distinguishability and obtain consistent results across multiple benchmarks. Implementation is available at https://github.com/abhrac/relational-proxies.

翻译：精细的类别在很大程度上具有相同的部分,不能仅仅根据部分信息而加以歧视,因为地方部分与对象的整体全球结构的关系方式大不相同。我们建议采用关系近似法,即利用一个对象的全球和地方观点之间的关系信息来编码其语义标签。我们从严格正式确定细微分类的区别概念开始,证明模型必须满足必要和充分的条件,以便了解细微环境的基本决定界限。我们根据理论调查结果设计关系近似法,并根据7个具有挑战性的细微基准数据集对它进行评估,并取得所有这些数据库的最新结果,在某些情况下超过所有现有工作的绩效,幅度超过4%以上。我们还试验性地验证了我们关于细微区别的理论,并在多个基准中取得一致的结果。执行情况见https://github.com/abhrac/relational-proxieceies。