CCFace: Classification Consistency for Low-Resolution Face Recognition

2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB(2023)

Cited 0|Views16
No score
Abstract
In recent years, deep face recognition methods have demonstrated impressive results on in-the-wild datasets. However, these methods have shown a significant decline in performance when applied to real-world low-resolution benchmarks like TinyFace or SCFace. To address this challenge, we propose a novel classification consistency knowledge distillation approach that transfers the learned classifier from a high-resolution model to a low-resolution network. This approach helps in finding discriminative representations for low-resolution instances. To further improve the performance, we designed a knowledge distillation loss using the adaptive angular penalty inspired by the success of the popular angular margin loss function. The adaptive penalty reduces overfitting on low-resolution samples and alleviates the convergence issue of the model integrated with data augmentation. Additionally, we utilize an asymmetric cross-resolution learning approach based on the state-of-the-art semi-supervised representation learning paradigm to improve discriminability on low-resolution instances and prevent them from forming a cluster. Our proposed method outperforms state-of-the-art approaches on low-resolution benchmarks, with a three percent improvement on TinyFace while maintaining performance on high-resolution benchmarks.
More
Translated text
Key words
Face Recognition,Low-resolution Face,Low-resolution Face Recognition,Loss Function,Data Augmentation,Representation Learning,Percentage Improvement,Training Dataset,High-resolution Images,Teacher Model,Large-scale Datasets,Generative Adversarial Networks,Latent Space,Low-resolution Images,Self-supervised Learning,Student Model,Convergence Problems,Teacher Network,Video Surveillance,Surveillance Cameras,Student Network,Low-resolution Model,Interclass Similarity,Low-resolution Input,Hypersphere,Low-resolution Data,Face Recognition Model,Marginal Value,Gradient Magnitude,Face Recognition Performance
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined