{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/face-hallucination-using-split-attention-in","title":"Face Hallucination via Split-Attention in Split-Attention Network","arxiv_id":"2010.11575","date":"2020-10-22","proceeding":null,"authors":["Tao Lu","Yuanzhi Wang","Yanduo Zhang","Yu Wang","Wei Liu","Zhongyuan Wang","Junjun Jiang"],"abstract":"Recently, convolutional neural networks (CNNs) have been widely employed to promote the face hallucination due to the ability to predict high-frequency details from a large number of samples. However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e.g., face detection, facial recognition). To tackle this issue, we propose a novel external-internal split attention group (ESAG), which encompasses two paths responsible for facial structure information and facial texture details, respectively. By fusing the features from these two paths, the consistency of facial structure and the fidelity of facial details are strengthened at the same time. Then, we propose a split-attention in split-attention network (SISN) to reconstruct photorealistic high-resolution facial images by cascading several ESAGs. Experimental results on face hallucination and face recognition unveil that the proposed method not only significantly improves the clarity of hallucinated faces, but also encourages the subsequent face recognition performance substantially. Codes have been released at https://github.com/mdswyz/SISN-Face-Hallucination.","url_abs":"https://arxiv.org/abs/2010.11575v3","url_pdf":"https://arxiv.org/pdf/2010.11575v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"face-hallucination-using-split-attention-in","repo_url":"https://github.com/mdswyz/SISN-Face-Hallucination","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"face-hallucination","task_name":"Face Hallucination"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"split-attention","method_name":"Split Attention"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}