{"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/causal-imagenet-how-to-discover-spurious-1","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","arxiv_id":"2110.04301","date":"2021-10-08","proceeding":null,"authors":["Sahil Singla","Soheil Feizi"],"abstract":"Deep neural networks can be unreliable in the real world especially when they heavily use {\\it spurious} features for their predictions. Focusing on image classifications, we define {\\it core features} as the set of visual features that are always a part of the object definition while {\\it spurious features} are the ones that are likely to {\\it co-occur} with the object but not a part of it (e.g., attribute \"fingers\" for class \"band aid\"). Traditional methods for discovering spurious features either require extensive human annotations (thus, not scalable), or are useful on specific models. In this work, we introduce a {\\it general} framework to discover a subset of spurious and core visual features used in inferences of a general model and localize them on a large number of images with minimal human supervision. Our methodology is based on this key idea: to identify spurious or core \\textit{visual features} used in model predictions, we identify spurious or core \\textit{neural features} (penultimate layer neurons of a robust model) via limited human supervision (e.g., using top 5 activating images per feature). We then show that these neural feature annotations {\\it generalize} extremely well to many more images {\\it without} any human supervision. We use the activation maps for these neural features as the soft masks to highlight spurious or core visual features. Using this methodology, we introduce the {\\it Salient Imagenet} dataset containing core and spurious masks for a large set of samples from Imagenet. Using this dataset, we show that several popular Imagenet models rely heavily on various spurious features in their predictions, indicating the standard accuracy alone is not sufficient to fully assess model performance. Code and dataset for reproducing all experiments in the paper is available at \\url{https://github.com/singlasahil14/salient_imagenet}.","url_abs":"https://arxiv.org/abs/2110.04301v4","url_pdf":"https://arxiv.org/pdf/2110.04301v4.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":"causal-imagenet-how-to-discover-spurious-1","repo_url":"https://github.com/singlasahil14/salient_imagenet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"causal-imagenet-how-to-discover-spurious-1","repo_url":"https://github.com/fraunhofer-aisec/shortcut-detection-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.04301","atlas_url":"https://app.syntology.ai/?focus=2110.04301","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":"2110.04301"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.04301\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.04301"},"call":"get_concepts_for_paper(arxiv_id=\"2110.04301\")"}],"by_repo":[{"repo":"singlasahil14/salient_imagenet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fraunhofer-aisec/shortcut-detection-vae","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2302.04246"],"harvested_for_calls":[{"arxiv_id":"2302.04246","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2302.04246"},"call":"get_harvested_code_for_paper(arxiv_id=\"2302.04246\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ea3560c0b5b23786dec9db1a01ddb4d2ac81270427cfc78b5935da0d556bbbd7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}