2025-01-14-mou25a.md

title	booktitle	year	volume	series	month	publisher	pdf	url	openreview	abstract	layout	issn	id	tex_title	firstpage	lastpage	page	order	cycles	bibtex_editor	editor	bibtex_author	author	date	address	container-title	genre	issued	extras
How Classification Baseline Works for Deep Metric Learning: A Perspective of Metric Space	Proceedings of the 16th Asian Conference on Machine Learning	2025	260	Proceedings of Machine Learning Research	0	PMLR	https://raw.githubusercontent.com/mlresearch/v260/main/assets/mou25a/mou25a.pdf	https://proceedings.mlr.press/v260/mou25a.html	DVl5GAuBXA	Deep Metric Learning (DML) stands as a powerful technique utilized for training models to capture semantic similarities between data points across various domains, including computer vision, natural language processing, and recommendation systems. Current approaches in DML often prioritize the development of novel network structures or loss functions while overlooking metric properties and the intricate relationship between classification and metric learning. This oversight results in significant time overhead, particularly when the number of categories increases. To address this challenge, we propose extending the loss function used in classification to function as a metric, thereby imposing constraints on the distances between training samples based on the triangle inequality. This approach is akin to proxy-based methods and aims to enhance the efficiency of DML. Drawing inspiration from metrically convex metrics, we introduce the concept of a "weak-metric" to overcome the limitations associated with certain loss functions that cannot be straightforwardly extended to full metrics. This ensures the effectiveness of DML under various circumstances. Furthermore, we extend the Cross Entropy loss function to function as a weak-metric and introduce a novel metric loss derived from Cross Entropy for experimental comparisons with other methods. The results underscore the credibility and reliability of our proposal, showcasing its superiority over state-of-the-art techniques. Notably, our approach also exhibits significantly faster training times as the number of categories increases, making it a compelling choice for large-scale datasets.	inproceedings	2640-3498	mou25a	{How Classification Baseline Works for Deep Metric Learning}: {A} Perspective of Metric Space	64	78	64-78	64	false	Nguyen, Vu and Lin, Hsuan-Tien	given family Vu Nguyen given family Hsuan-Tien Lin	Mou, Yuanqu and Jian, Zhengxue and Bai, Haiyang and Gou, Chang	given family Yuanqu Mou given family Zhengxue Jian given family Haiyang Bai given family Chang Gou	2025-01-14		Proceedings of the 16th Asian Conference on Machine Learning	inproceedings	date-parts 2025 1 14	label link Supplementary PDF https://raw.githubusercontent.com/mlresearch/v260/main/assets/assets/mou25a/mou25a-supp.pdf