Ef-QuantFace: Streamlined Face Recognition with Small Data and Low-Bit Precision

arXiv:2402.18163v1 Announce Type: new
Abstract: In recent years, model quantization for face recognition has gained prominence. Traditionally, compressing models involved vast datasets like the 5.8 million-image MS1M dataset as well as extensive training times, raising the question of whether such data enormity is essential. This paper addresses this by introducing an efficiency-driven approach, fine-tuning the model with just up to 14,000 images, 440 times smaller than MS1M. We demonstrate that effective quantization is achievable with a smaller dataset, presenting a …

abstract arxiv cs.cv data dataset datasets face face recognition image low paper precision quantization question recognition small small data training type vast