Anti-collapse Loss For Deep Metric Learning Based On Coding Rate Metric

Abstract

Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature predominantly focuses on pair-based and proxy-based methods to maximize inter-class discrepancy and minimize intra-class diversity. However, these methods tend to suffer from the collapse of the embedding space due to their over-reliance on label information. This leads to sub-optimal feature representation and inferior model performance. To maintain the structure of embedding space and avoid feature collapse, we propose a novel loss function called Anti-Collapse Loss. Specifically, our proposed loss primarily draws inspiration from the principle of Maximal Coding Rate Reduction. It promotes the sparseness of feature clusters in the embedding space to prevent collapse by maximizing the average coding rate of sample features or class proxies. Moreover, we integrate our proposed loss with pair-based and proxy-base

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjiang2024anti

Related papers

• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16
• Ranked List Loss For Deep Metric Learning (2019)7.50
• Constellation Loss: Improving The Efficiency Of Deep Metric Learning Loss Functions For Optimal Embedding (2019)0.00
• The Group Loss For Deep Metric Learning (2019)11.39
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• The General Pair-based Weighting Loss For Deep Metric Learning (2019)0.00
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08
• Rethinking Preventing Class-collapsing In Metric Learning With Margin-based Losses (2020)9.23