DIABLO: Dictionary-based Attention Block For Deep Metric Learning

Abstract

Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks. Recent contributions mostly address the training part (loss functions, sampling strategies, etc.), while a few works focus on improving the discriminative power of the image representation. In this paper, we propose DIABLO, a dictionary-based attention method for image embedding. DIABLO produces richer representations by aggregating only visually-related features together while being easier to train than other attention-based methods in deep metric learning. This is experimentally confirmed on four deep metric learning datasets (Cub-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval) for which DIABLO shows state-of-the-art performances.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyjacob2020diablo

Related papers

• Attention-based Ensemble For Deep Metric Learning (2018)15.90
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Indirect: Language-guided Zero-shot Deep Metric Learning For Images (2022)5.24
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Hybrid-attention Based Decoupled Metric Learning For Zero-shot Image Retrieval (2019)12.93
• Three Things To Know About Deep Metric Learning (2024)0.00
• Diva: Diverse Visual Feature Aggregation For Deep Metric Learning (2020)11.58
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00