{"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/m2tr-multi-modal-multi-scale-transformers-for","title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection","arxiv_id":"2104.09770","date":"2021-04-20","proceeding":null,"authors":["Junke Wang","Zuxuan Wu","Wenhao Ouyang","Xintong Han","Jingjing Chen","Ser-Nam Lim","Yu-Gang Jiang"],"abstract":"The widespread dissemination of Deepfakes demands effective approaches that can detect perceptually convincing forged images. In this paper, we aim to capture the subtle manipulation artifacts at different scales using transformer models. In particular, we introduce a Multi-modal Multi-scale TRansformer (M2TR), which operates on patches of different sizes to detect local inconsistencies in images at different spatial levels. M2TR further learns to detect forgery artifacts in the frequency domain to complement RGB information through a carefully designed cross modality fusion block. In addition, to stimulate Deepfake detection research, we introduce a high-quality Deepfake dataset, SR-DF, which consists of 4,000 DeepFake videos generated by state-of-the-art face swapping and facial reenactment methods. We conduct extensive experiments to verify the effectiveness of the proposed method, which outperforms state-of-the-art Deepfake detection methods by clear margins.","url_abs":"https://arxiv.org/abs/2104.09770v3","url_pdf":"https://arxiv.org/pdf/2104.09770v3.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":"m2tr-multi-modal-multi-scale-transformers-for","repo_url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"m2tr-multi-modal-multi-scale-transformers-for","repo_url":"https://github.com/wangjk666/PyDeepFakeDet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"m2tr-multi-modal-multi-scale-transformers-for","repo_url":"https://github.com/Recognito-Vision/Linux-FaceRecognition-FaceLivenessDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.09770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09770"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Recognito-Vision/Linux-FaceRecognition-FaceLivenessDetection","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangjk666/PyDeepFakeDet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":3,"ran_fixture":1,"unverified":7},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1},"listed":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"97170801bfeabdb7","entry":"DCT_mat","repo":"wangjk666/PyDeepFakeDet","repo_kind":"listed","path":"PyDeepFakeDet/models/f3net.py","file_url":"https://github.com/wangjk666/PyDeepFakeDet/blob/HEAD/PyDeepFakeDet/models/f3net.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97170801bfeabdb7"}},{"code_sha256_prefix":"971ae8d2d8313e30","entry":"drop_path","repo":"wangjk666/PyDeepFakeDet","repo_kind":"listed","path":"PyDeepFakeDet/models/vit.py","file_url":"https://github.com/wangjk666/PyDeepFakeDet/blob/HEAD/PyDeepFakeDet/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"code_sha256_prefix":"22f1a0ed4d350586","entry":"norm_sigma","repo":"wangjk666/PyDeepFakeDet","repo_kind":"listed","path":"PyDeepFakeDet/models/f3net.py","file_url":"https://github.com/wangjk666/PyDeepFakeDet/blob/HEAD/PyDeepFakeDet/models/f3net.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22f1a0ed4d350586"}},{"code_sha256_prefix":"f93cb693ac8bb537","entry":"round_repeats","repo":"wangjk666/PyDeepFakeDet","repo_kind":"listed","path":"PyDeepFakeDet/models/efficientnet.py","file_url":"https://github.com/wangjk666/PyDeepFakeDet/blob/HEAD/PyDeepFakeDet/models/efficientnet.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f93cb693ac8bb537"}},{"code_sha256_prefix":"087ffc0296348717","entry":"attention","repo":"wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","repo_kind":"official","path":"M2TR/models/m2tr.py","file_url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection/blob/HEAD/M2TR/models/m2tr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"087ffc0296348717"}},{"code_sha256_prefix":"45eada2b88e70500","entry":"drop_connect","repo":"wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","repo_kind":"official","path":"M2TR/models/efficientnet.py","file_url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection/blob/HEAD/M2TR/models/efficientnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45eada2b88e70500"}},{"code_sha256_prefix":"e10d6bd8a13ae5dc","entry":"generate_filter","repo":"wangjk666/PyDeepFakeDet","repo_kind":"listed","path":"PyDeepFakeDet/models/f3net.py","file_url":"https://github.com/wangjk666/PyDeepFakeDet/blob/HEAD/PyDeepFakeDet/models/f3net.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e10d6bd8a13ae5dc"}},{"code_sha256_prefix":"50a33c8f97a28b13","entry":"get_augmentations_from_list","repo":"wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","repo_kind":"official","path":"M2TR/datasets/utils.py","file_url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection/blob/HEAD/M2TR/datasets/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50a33c8f97a28b13"}},{"code_sha256_prefix":"9443a182bc244501","entry":"get_transformations","repo":"wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","repo_kind":"official","path":"M2TR/datasets/utils.py","file_url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection/blob/HEAD/M2TR/datasets/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9443a182bc244501"}},{"code_sha256_prefix":"fea14f1f6c2644bf","entry":"round_filters","repo":"wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","repo_kind":"official","path":"M2TR/models/efficientnet.py","file_url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection/blob/HEAD/M2TR/models/efficientnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fea14f1f6c2644bf"}},{"code_sha256_prefix":"681a914bf36790de","entry":"transforms_mask","repo":"wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection","repo_kind":"official","path":"M2TR/datasets/utils.py","file_url":"https://github.com/wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection/blob/HEAD/M2TR/datasets/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"681a914bf36790de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}