Introspective Deep Metric Learning

Abstract

This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images. Conventional deep metric learning methods focus on learning a discriminative embedding to describe the semantic features of images, which ignore the existence of uncertainty in each image resulting from noise or semantic ambiguity. Training without awareness of these uncertainties causes the model to overfit the annotated labels during training and produce unsatisfactory judgments during inference. Motivated by this, we argue that a good similarity model should consider the semantic discrepancies with awareness of the uncertainty to better deal with ambiguous images for more robust training. To achieve this, we propose to represent an image using not only a semantic embedding but also an accompanying uncertainty embedding, which describes the semantic characteristics and ambiguity of an image, respectively. We further propose an introspective similarity metric to make

Stats

• citations23
• S2 citations—
• github stars55
• HF likes0
• heat score13.85
• arxiv keywang2023introspective

Related papers

• Introspective Deep Metric Learning For Image Retrieval (2022)3.50
• Calibrated Neighborhood Aware Confidence Measure For Deep Metric Learning (2020)0.00
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• Hyp-uml: Hyperbolic Image Retrieval With Uncertainty-aware Metric Learning (2023)0.00
• Three Things To Know About Deep Metric Learning (2024)0.00
• Towards Interpretable Deep Metric Learning With Structural Matching (2021)15.87
• Integrating Language Guidance Into Vision-based Deep Metric Learning (2022)14.04