Scaleface: Uncertainty-aware Deep Metric Learning

Abstract

The performance of modern deep learning-based systems dramatically depends on the quality of input objects. For example, face recognition quality would be lower for blurry or corrupted inputs. However, it is hard to predict the influence of input quality on the resulting accuracy in more complex scenarios. We propose an approach for deep metric learning that allows direct estimation of the uncertainty with almost no additional computational cost. The developed \textit\{ScaleFace\} algorithm uses trainable scale values that modify similarities in the space of embeddings. These input-dependent scale values represent a measure of confidence in the recognition result, thus allowing uncertainty estimation. We provide comprehensive experiments on face recognition tasks that show the superior performance of ScaleFace compared to other uncertainty-aware face recognition approaches. We also extend the results to the task of text-to-image retrieval showing that the proposed approach beats the co

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keykail2022scaleface

Related papers

• Calibrated Neighborhood Aware Confidence Measure For Deep Metric Learning (2020)0.00
• Introspective Deep Metric Learning (2023)13.85
• Introspective Deep Metric Learning For Image Retrieval (2022)3.50
• Probabilistic Embeddings Revisited (2022)5.84
• Cp-mtml: Coupled Projection Multi-task Metric Learning For Large Scale Face Retrieval (2016)11.67
• Deep Metric Structured Learning For Facial Expression Recognition (2020)0.00
• Learning A Metric Embedding For Face Recognition Using The Multibatch Method (2016)0.00
• Bayesian Metric Learning For Uncertainty Quantification In Image Retrieval (2023)0.00