Relational Proxies: Emergent Relationships as Fine-Grained DiscriminatorsDownload PDF

Published: 31 Oct 2022, Last Modified: 03 Jul 2024NeurIPS 2022 AcceptReaders: Everyone
Keywords: Fine-grained visual categorization, Relational learning, Information theory
TL;DR: We present a rigorous, information theoretic formalization of fine-grained visual categorization, designing a method based on the provable semantic relevance of emergent relationships between local and global views of an object.
Abstract: 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.
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/relational-proxies-emergent-relationships-as/code)
19 Replies

Loading