Litcius/Paper detail

Learning Spatial-Semantic Relationship for Facial Attribute Recognition with Limited Labeled Data

Ying Shu, Yan Yan, Si Chen, Jing‐Hao Xue, Chunhua Shen, Hanzi Wang

202138 citationsDOIOpen Access PDF

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 self-supervised 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.

Topics & Concepts

Computer scienceArtificial intelligenceTask (project management)Pattern recognition (psychology)SegmentationMulti-task learningParsingSpatial analysisDeep learningTask analysisNatural language processingMachine learningGeologyEconomicsRemote sensingManagementFace recognition and analysisFace and Expression RecognitionFacial Nerve Paralysis Treatment and Research
Learning Spatial-Semantic Relationship for Facial Attribute Recognition with Limited Labeled Data | Litcius