{"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/measuring-the-interpretability-of","title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing","arxiv_id":null,"date":"2021-09-29","proceeding":"ICLR 2022 4","authors":["Iro Laina","Yuki M Asano","Andrea Vedaldi"],"abstract":"Self-supervised visual representation learning has attracted significant research interest. While the most common way to evaluate self-supervised representations is through transfer to various downstream tasks, we instead investigate the problem of measuring their interpretability, i.e. understanding the semantics encoded in the raw representations. We formulate the latter as estimating the mutual information between the representation and a space of manually labelled concepts. To quantify this we introduce a decoding bottleneck: information must be captured by simple predictors, mapping concepts to clusters of data formed in representation space. This approach, which we call reverse linear probing, provides a single number sensitive to the semanticity of the representation. This measure is also able to detect when the representation correlates with combinations of labelled concepts (e.g. \"red apple\") instead of just individual attributes (\"red\" and \"apple\" separately). Finally, we also suggest that supervised classifiers can be used to automatically label large datasets with a rich space of attributes. We use these insights to evaluate a large number of self-supervised representations, ranking them by interpretability, and highlight the differences that emerge compared to the standard evaluation with linear probes.","url_abs":"https://openreview.net/forum?id=HFPTzdwN39","url_pdf":"https://openreview.net/pdf?id=HFPTzdwN39","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":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"SeLa(v2) (reverse linear probing)","rank_in_archive_order":90,"of":106,"metrics":{"Top-1 Accuracy":"20.61","Top-5 Accuracy":"48.83"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"DeepCluster(v2) (reverse linear probing)","rank_in_archive_order":92,"of":106,"metrics":{"Top-1 Accuracy":"19.73","Top-5 Accuracy":"46.81"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"SwAV (reverse linear probing)","rank_in_archive_order":95,"of":106,"metrics":{"Top-1 Accuracy":"17.71","Top-5 Accuracy":"43.64"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"MoCo(v2) (reverse linear probing)","rank_in_archive_order":101,"of":106,"metrics":{"Top-1 Accuracy":"12.67","Top-5 Accuracy":"31.45"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"MoCHi  (reverse linear probing)","rank_in_archive_order":102,"of":106,"metrics":{"Top-1 Accuracy":"12.64","Top-5 Accuracy":"31.71"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"OBoW (reverse linear probing)","rank_in_archive_order":103,"of":106,"metrics":{"Top-1 Accuracy":"12.23","Top-5 Accuracy":"31.72"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"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":"ebe70f7188fa7ec783adc99c734d74755b3ceb9f72f12b95df232bd18fc526c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}