Deep Metric Learning With Soft Orthogonal Proxies

Abstract

Deep Metric Learning (DML) models rely on strong representations and similarity-based measures with specific loss functions. Proxy-based losses have shown great performance compared to pair-based losses in terms of convergence speed. However, proxies that are assigned to different classes may end up being closely located in the embedding space and hence having a hard time to distinguish between positive and negative items. Alternatively, they may become highly correlated and hence provide redundant information with the model. To address these issues, we propose a novel approach that introduces Soft Orthogonality (SO) constraint on proxies. The constraint ensures the proxies to be as orthogonal as possible and hence control their positions in the embedding space. Our approach leverages Data-Efficient Image Transformer (DeiT) as an encoder to extract contextual features from images along with a DML objective. The objective is made of the Proxy Anchor loss along with the SO regularization

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysaberimovahed2023deep

Related papers

• Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation (2024)6.34
• No Fuss Distance Metric Learning Using Proxies (2017)20.03
• Hierarchical Proxy-based Loss For Deep Metric Learning (2021)10.85
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• Proxy Synthesis: Learning With Synthetic Classes For Deep Metric Learning (2021)10.85
• Procsim: Proxy-based Confidence For Robust Similarity Learning (2023)0.00
• Robust Calibrate Proxy Loss For Deep Metric Learning (2023)0.00
• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16