Exploring Transfer Learning on Face Recognition of Dark Skinned, Low Quality and Low Resource Face Data
This work addresses the problem of biased face recognition models for dark-skinned individuals, particularly in low-resource settings, which is a significant issue for equitable AI development.
This paper explores transfer learning for face recognition on dark-skinned, low-quality, and low-resource Ethiopian face data. By applying transfer learning on VGGFace, the authors achieved over 95% accuracy, demonstrating its effectiveness in this challenging setting.
There is a big difference in the tone of color of skin between dark and light skinned people. Despite this fact, most face recognition tasks almost all classical state-of-the-art models are trained on datasets containing an overwhelming majority of light skinned face images. It is tedious to collect a huge amount of data for dark skinned faces and train a model from scratch. In this paper, we apply transfer learning on VGGFace to check how it works on recognising dark skinned mainly Ethiopian faces. The dataset is of low quality and low resource. Our experimental results show above 95\% accuracy which indicates that transfer learning in such settings works.