{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/turning-a-blind-eye-explicit-removal-of","title":"Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings","arxiv_id":"1809.02169","date":"2018-09-06","proceeding":null,"authors":["Mohsan Alvi","Andrew Zisserman","Christoffer Nellaker"],"abstract":"Neural networks achieve the state-of-the-art in image classification tasks.\nHowever, they can encode spurious variations or biases that may be present in\nthe training data. For example, training an age predictor on a dataset that is\nnot balanced for gender can lead to gender biased predicitons (e.g. wrongly\npredicting that males are older if only elderly males are in the training set).\nWe present two distinct contributions: 1) An algorithm that can remove multiple\nsources of variation from the feature representation of a network. We\ndemonstrate that this algorithm can be used to remove biases from the feature\nrepresentation, and thereby improve classification accuracies, when training\nnetworks on extremely biased datasets. 2) An ancestral origin database of\n14,000 images of individuals from East Asia, the Indian subcontinent,\nsub-Saharan Africa, and Western Europe. We demonstrate on this dataset, for a\nnumber of facial attribute classification tasks, that we are able to remove\nracial biases from the network feature representation.","url_abs":"http://arxiv.org/abs/1809.02169v2","url_pdf":"http://arxiv.org/pdf/1809.02169v2.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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[{"slug":"laofiw-dataset","name":"LAOFIW Dataset","full_name":"Labeled Ancestral Origin Faces in the Wild"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.02169","atlas_url":"https://app.syntology.ai/?focus=1809.02169","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1809.02169"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.02169\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.02169"},"call":"get_concepts_for_paper(arxiv_id=\"1809.02169\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"271ee85eef5952eccbf54d14c7f8aa9af0b56515160550d5097be31251ffea67","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}