DIABLO: Dictionary-based Attention Block for Deep Metric Learning
This addresses the need for better image representations in metric learning, though it appears incremental as it builds on existing attention-based methods.
The paper tackles the problem of improving discriminative power in deep metric learning by proposing DIABLO, a dictionary-based attention method for image embedding, which achieves state-of-the-art performances on four datasets.
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.