Octuplet Loss: Make Face Recognition Robust to Image Resolution
arXiv:2207.06726 · doi:10.1109/FG57933.2023.10042669
Abstract
Image resolution, or in general, image quality, plays an essential role in the performance of today's face recognition systems. To address this problem, we propose a novel combination of the popular triplet loss to improve robustness against image resolution via fine-tuning of existing face recognition models. With octuplet loss, we leverage the relationship between high-resolution images and their synthetically down-sampled variants jointly with their identity labels. Fine-tuning several state-of-the-art approaches with our method proves that we can significantly boost performance for cross-resolution (high-to-low resolution) face verification on various datasets without meaningfully exacerbating the performance on high-to-high resolution images. Our method applied on the FaceTransformer network achieves 95.12% face verification accuracy on the challenging XQLFW dataset while reaching 99.73% on the LFW database. Moreover, the low-to-low face verification accuracy benefits from our method. We release our code to allow seamless integration of the octuplet loss into existing frameworks.
References in corpus (13)
- FaceNet: A Unified Embedding for Face Recognition and Clustering
- Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
- In Defense of the Triplet Loss for Person Re-Identification
- Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
- Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation
- SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
- Cross-Resolution Learning for Face Recognition
- Edge and Identity Preserving Network for Face Super-Resolution
- Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments
- Face Recognition in Low Quality Images: A Survey
- Face Transformer for Recognition
- Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network
- Homogeneous Low-Resolution Face Recognition Method based Correlation Features