Energy Confused Adversarial Metric Learning For Zero-shot Image Retrieval And Clustering

Abstract

Deep metric learning has been widely applied in many computer vision tasks, and recently, it is more attractive in *zero-shot image retrieval and clustering*(ZSRC) where a good embedding is requested such that the unseen classes can be distinguished well. Most existing works deem this 'good' embedding just to be the discriminative one and thus race to devise powerful metric objectives or hard-sample mining strategies for leaning discriminative embedding. However, in this paper, we first emphasize that the generalization ability is a core ingredient of this 'good' embedding as well and largely affects the metric performance in zero-shot settings as a matter of fact. Then, we propose the Energy Confused Adversarial Metric Learning(ECAML) framework to explicitly optimize a robust metric. It is mainly achieved by introducing an interesting Energy Confusion regularization term, which daringly breaks away from the traditional metric learning idea of discriminative objective devising, and see

Stats

• citations20
• S2 citations—
• github stars0
• HF likes0
• heat score9.92
• arxiv keychen2019energy

Related papers

• Hybrid-attention Based Decoupled Metric Learning For Zero-shot Image Retrieval (2019)12.93
• Deep Relational Metric Learning (2021)12.17
• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach For Feature Embedding (2020)2.26
• Indirect: Language-guided Zero-shot Deep Metric Learning For Images (2022)5.24
• Directional Statistics-based Deep Metric Learning For Image Classification And Retrieval (2018)13.05
• Modality-aware Triplet Hard Mining For Zero-shot Sketch-based Image Retrieval (2021)1.81
• Attention-based Ensemble For Deep Metric Learning (2018)15.90