{"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/locate-and-verify-a-two-stream-network-for","title":"Locate and Verify: A Two-Stream Network for Improved Deepfake Detection","arxiv_id":"2309.11131","date":"2023-09-20","proceeding":null,"authors":["Chao Shuai","Jieming Zhong","Shuang Wu","Feng Lin","Zhibo Wang","Zhongjie Ba","Zhenguang Liu","Lorenzo Cavallaro","Kui Ren"],"abstract":"Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently occurring but relatively unimportant in the training dataset. Furthermore, current methods heavily rely on a few dominant forgery regions and may ignore other equally important regions, leading to inadequate uncovering of forgery cues. In this paper, we strive to address these shortcomings from three aspects: (1) We propose an innovative two-stream network that effectively enlarges the potential regions from which the model extracts forgery evidence. (2) We devise three functional modules to handle the multi-stream and multi-scale features in a collaborative learning scheme. (3) Confronted with the challenge of obtaining forgery annotations, we propose a Semi-supervised Patch Similarity Learning strategy to estimate patch-level forged location annotations. Empirically, our method demonstrates significantly improved robustness and generalizability, outperforming previous methods on six benchmarks, and improving the frame-level AUC on Deepfake Detection Challenge preview dataset from 0.797 to 0.835 and video-level AUC on CelebDF$\\_$v1 dataset from 0.811 to 0.847. Our implementation is available at https://github.com/sccsok/Locate-and-Verify.","url_abs":"https://arxiv.org/abs/2309.11131v1","url_pdf":"https://arxiv.org/pdf/2309.11131v1.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":"locate-and-verify-a-two-stream-network-for","repo_url":"https://github.com/sccsok/Locate-and-Verify","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"face-swapping","task_name":"Face Swapping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2309.11131","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}