A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks

Abstract

Metric learning algorithms aim to learn a distance function that brings the semantically similar data items together and keeps dissimilar ones at a distance. The traditional Mahalanobis distance learning is equivalent to find a linear projection. In contrast, Deep Metric Learning (DML) methods are proposed that automatically extract features from data and learn a non-linear transformation from input space to a semantically embedding space. Recently, many DML methods are proposed focused to enhance the discrimination power of the learned metric by providing novel sampling strategies or loss functions. This approach is very helpful when both the training and test examples are coming from the same set of categories. However, it is less effective in many applications of DML such as image retrieval and person-reidentification. Here, the DML should learn general semantic concepts from observed classes and employ them to rank or identify objects from unseen categories. Neglecting the generali

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keyalkaabi2021a

Related papers

• Guided Deep Metric Learning (2022)6.77
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08
• Learning With Memory-based Virtual Classes For Deep Metric Learning (2021)9.92
• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Integrating Language Guidance Into Vision-based Deep Metric Learning (2022)14.04
• Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation (2024)6.34