{"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/forte-finding-outliers-with-representation","title":"Forte : Finding Outliers with Representation Typicality Estimation","arxiv_id":"2410.01322","date":"2024-10-02","proceeding":null,"authors":["Debargha Ganguly","Warren Morningstar","Andrew Yu","Vipin Chaudhary"],"abstract":"Generative models can now produce photorealistic synthetic data which is virtually indistinguishable from the real data used to train it. This is a significant evolution over previous models which could produce reasonable facsimiles of the training data, but ones which could be visually distinguished from the training data by human evaluation. Recent work on OOD detection has raised doubts that generative model likelihoods are optimal OOD detectors due to issues involving likelihood misestimation, entropy in the generative process, and typicality. We speculate that generative OOD detectors also failed because their models focused on the pixels rather than the semantic content of the data, leading to failures in near-OOD cases where the pixels may be similar but the information content is significantly different. We hypothesize that estimating typical sets using self-supervised learners leads to better OOD detectors. We introduce a novel approach that leverages representation learning, and informative summary statistics based on manifold estimation, to address all of the aforementioned issues. Our method outperforms other unsupervised approaches and achieves state-of-the art performance on well-established challenging benchmarks, and new synthetic data detection tasks.","url_abs":"https://arxiv.org/abs/2410.01322v2","url_pdf":"https://arxiv.org/pdf/2410.01322v2.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":"forte-finding-outliers-with-representation","repo_url":"https://github.com/DebarghaG/forte","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/out-of-distribution-detection-on-cifar-10-vs","task":"Out-of-Distribution Detection","dataset":"CIFAR-10 vs CIFAR-100","model":"Forte","rank_in_archive_order":5,"of":14,"metrics":{"AUPR":" 09.69 ± 01.08","AUROC":"97.63 ± 00.15"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-cifar-10-vs-2","task":"Out-of-Distribution Detection","dataset":"CIFAR-10 vs SVHN","model":"Forte","rank_in_archive_order":2,"of":3,"metrics":{"AUROC":"99.84 ± 00.05","FPR95":"00.00 ± 00.00"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-13","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs NINCO","model":"Forte","rank_in_archive_order":1,"of":5,"metrics":{"AUROC":"98.34 ± 00.09","FPR@95":"5.18 ± 00.51"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-11","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs OpenImage-O","model":"Forte","rank_in_archive_order":3,"of":7,"metrics":{"AUROC":"96.73 ± 00.11","FPR95":"11.77 ± 00.57"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-10","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Textures","model":"Forte","rank_in_archive_order":2,"of":34,"metrics":{"AUROC":"98.04 ± 00.10","FPR95":"5.61 ± 00.25"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-3","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs iNaturalist","model":"Forte","rank_in_archive_order":1,"of":28,"metrics":{"AUROC":"99.67 ± 00.03","FPR95":"0.64 ± 00.06"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.01322","atlas_url":"https://app.syntology.ai/?focus=2410.01322","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":"2410.01322"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.01322\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.01322"},"call":"get_concepts_for_paper(arxiv_id=\"2410.01322\")"}],"by_repo":[{"repo":"DebarghaG/forte","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"5989384da27f72cdcb562e526054772a35bf7ddf0dc8a488f3d0fed5c52ccc61","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}