{"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/iml-vit-image-manipulation-localization-by","title":"IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer","arxiv_id":"2307.14863","date":"2023-07-27","proceeding":null,"authors":["Xiaochen Ma","Bo Du","Zhuohang Jiang","Xia Du","Ahmed Y. Al Hammadi","Jizhe Zhou"],"abstract":"Advanced image tampering techniques are increasingly challenging the trustworthiness of multimedia, leading to the development of Image Manipulation Localization (IML). But what makes a good IML model? The answer lies in the way to capture artifacts. Exploiting artifacts requires the model to extract non-semantic discrepancies between manipulated and authentic regions, necessitating explicit comparisons between the two areas. With the self-attention mechanism, naturally, the Transformer should be a better candidate to capture artifacts. However, due to limited datasets, there is currently no pure ViT-based approach for IML to serve as a benchmark, and CNNs dominate the entire task. Nevertheless, CNNs suffer from weak long-range and non-semantic modeling. To bridge this gap, based on the fact that artifacts are sensitive to image resolution, amplified under multi-scale features, and massive at the manipulation border, we formulate the answer to the former question as building a ViT with high-resolution capacity, multi-scale feature extraction capability, and manipulation edge supervision that could converge with a small amount of data. We term this simple but effective ViT paradigm IML-ViT, which has significant potential to become a new benchmark for IML. Extensive experiments on three different mainstream protocols verified our model outperforms the state-of-the-art manipulation localization methods. Code and models are available at https://github.com/SunnyHaze/IML-ViT.","url_abs":"https://arxiv.org/abs/2307.14863v4","url_pdf":"https://arxiv.org/pdf/2307.14863v4.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":"iml-vit-image-manipulation-localization-by","repo_url":"https://github.com/sunnyhaze/iml-vit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"image-manipulation","task_name":"Image Manipulation"},{"task_slug":"image-manipulation-localization","task_name":"Image Manipulation Localization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-manipulation-localization-on-casiav1","task":"Image Manipulation Localization","dataset":"CASIAv1(Protoclo-CAT)","model":"IML-ViT","rank_in_archive_order":4,"of":8,"metrics":{"Pixel Binary F1":"0.795"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-coverage-1","task":"Image Manipulation Localization","dataset":"COVERAGE(Protocol-CAT)","model":"IML-ViT","rank_in_archive_order":1,"of":8,"metrics":{"Pixel Binary F1":"0.654"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-columbia-1","task":"Image Manipulation Localization","dataset":"Columbia(Protocol-CAT)","model":"IML-ViT","rank_in_archive_order":1,"of":8,"metrics":{"Pixel Binary F1":"0.948"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-nist16","task":"Image Manipulation Localization","dataset":"NIST16(Protocol-CAT)","model":"IML-ViT","rank_in_archive_order":1,"of":8,"metrics":{"Pixel Binary F1":"0.501"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.14863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14863"}},"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/sunnyhaze/iml-vit","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"1d5da97bb67bcbb1","entry":"denormalize","repo":"sunnyhaze/iml-vit","repo_kind":"official","path":"utils/datasets.py","file_url":"https://github.com/sunnyhaze/iml-vit/blob/HEAD/utils/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d5da97bb67bcbb1"}},{"code_sha256_prefix":"f67f7fd670b8667b","entry":"pil_loader","repo":"sunnyhaze/iml-vit","repo_kind":"official","path":"utils/datasets.py","file_url":"https://github.com/sunnyhaze/iml-vit/blob/HEAD/utils/datasets.py","link_basis":"first_harvest_node","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":"f67f7fd670b8667b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}