Shu, Y; Yan, Y; Chen, S; Xue, J; Shen, C; Wang, H; (2021) Learning Spatial-Semantic Relationship for Facial Attribute Recognition With Limited Labeled Data. In: (Proceedings) IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (In press).

Preview

Text YingShu-03649-final.pdf - Accepted Version Download (815kB) | Preview

Abstract

Recent advances in deep learning have demonstrated excellent results for Facial Attribute Recognition (FAR), typically trained with large-scale labeled data. However, in many real-world FAR applications, only limited labeled data are available, leading to remarkable deterioration in performance for most existing deep learning-based FAR methods. To address this problem, here we propose a method termed Spatial-Semantic Patch Learning (SSPL). The training of SSPL involves two stages. First, three auxiliary tasks, consisting of a Patch Rotation Task (PRT), a Patch Segmentation Task (PST), and a Patch Classification Task (PCT), are jointly developed to learn the spatial-semantic relationship from large-scale unlabeled facial data. We thus obtain a powerful pre-trained model. In particular, PRT exploits the spatial information of facial images in a selfsupervised learning manner. PST and PCT respectively capture the pixel-level and image-level semantic information of facial images based on a facial parsing model. Second, the spatial-semantic knowledge learned from auxiliary tasks is transferred to the FAR task. By doing so, it enables that only a limited number of labeled data are required to fine-tune the pre-trained model. We achieve superior performance compared with state-of-the-art methods, as substantiated by extensive experiments and studies.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item