2022/09/05 by Roman Kail, Kirill Fedyanin, Kail, Roman +7
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2209.01880
openalex publication_date 2022/09/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
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 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 competitors with significant margin.