Work

Deep Disentangled Metric Learning

Year: 2025

Type: conference-paper

Abstract: Proxy-based metric learning has enhanced semantic similarity with class representatives and exhibited noteworthy performance in deep metric learning (DML) tasks. While these methods alleviate computational demands by learning instance-to-class relationships rather than instance-to-instance relationships, they often limit features to be class-specific, thereby degrading generalization performance for unseen class. In this paper, we introduce a novel perspective called Disentangled Deep Metric Learning (DDML), grounded in the framework of information bottleneck, which applies class-agnostic regularization to existing DML methods. Unlike conventional NormSoftmax methods, which primarily emphasize distinct class-specific features, our DDML enables a diverse feature representation by seamlessly transitioning between class-specific features with the aid of class-agnostic features. It smooths decision boundaries, allowing unseen classes to have stable semantic representations in the embedding space. To achieve this, we learn disentangled representations of both class-specific and class-agnostic features in the context of DML. Empirical results demonstrate that our method addresses the limitations of conventional approaches. Our method easily integrates into existing proxy-based algorithms, consistently delivering improved performance.

Source: Proceedings of the AAAI Conference on Artificial Intelligence

DOI: 10.1609/aaai.v39i19.34184

Authors: Jinhee Park, Jisoo Park, Dagyeong Na, Junseok Kwon

Institution: Chung-Ang University

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: Chung-Ang University, Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion

Awards: G1768175725, G4447557280, G614672494