Attention-based Ensemble For Deep Metric Learning

Abstract

Deep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space. Recently, ensemble has been applied to deep metric learning to yield state-of-the-art results. As one important aspect of ensemble, the learners should be diverse in their feature embeddings. To this end, we propose an attention-based ensemble, which uses multiple attention masks, so that each learner can attend to different parts of the object. We also propose a divergence loss, which encourages diversity among the learners. The proposed method is applied to the standard benchmarks of deep metric learning and experimental results show that it outperforms the state-of-the-art methods by a significant margin on image retrieval tasks.

Stats

• citations131
• S2 citations—
• github stars0
• HF likes0
• heat score15.90
• arxiv keykim2018attention

Related papers

• Deep Randomized Ensembles For Metric Learning (2018)13.97
• Three Things To Know About Deep Metric Learning (2024)0.00
• DIABLO: Dictionary-based Attention Block For Deep Metric Learning (2020)2.26
• 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
• Learning Intra-batch Connections For Deep Metric Learning (2021)0.00
• The Group Loss For Deep Metric Learning (2019)11.39
• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16