Adaptive Additive Classification-based Loss For Deep Metric Learning

Abstract

Recent works have shown that deep metric learning algorithms can benefit from weak supervision from another input modality. This additional modality can be incorporated directly into the popular triplet-based loss function as distances. Also recently, classification loss and proxy-based metric learning have been observed to lead to faster convergence as well as better retrieval results, all the while without requiring complex and costly sampling strategies. In this paper we propose an extension to the existing adaptive margin for classification-based deep metric learning. Our extension introduces a separate margin for each negative proxy per sample. These margins are computed during training from precomputed distances of the classes in the other modality. Our results set a new state-of-the-art on both on the Amazon fashion retrieval dataset as well as on the public DeepFashion dataset. This was observed with both fastText- and BERT-based embeddings for the additional textual modality.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfehervari2020adaptive

Related papers

• Hierarchical Proxy-based Loss For Deep Metric Learning (2021)10.85
• Rethinking Preventing Class-collapsing In Metric Learning With Margin-based Losses (2020)9.23
• DAAL: Density-aware Adaptive Line Margin Loss For Multi-modal Deep Metric Learning (2024)0.00
• Constellation Loss: Improving The Efficiency Of Deep Metric Learning Loss Functions For Optimal Embedding (2019)0.00
• Shadow Loss: Memory-linear Deep Metric Learning For Efficient Training (2023)0.00
• Robust Calibrate Proxy Loss For Deep Metric Learning (2023)0.00
• Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation (2024)6.34
• Proxy Synthesis: Learning With Synthetic Classes For Deep Metric Learning (2021)10.85