{"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/representation-learning-by-learning-to-count","title":"Representation Learning by Learning to Count","arxiv_id":"1708.06734","date":"2017-08-22","proceeding":"ICCV 2017 10","authors":["Mehdi Noroozi","Hamed Pirsiavash","Paolo Favaro"],"abstract":"We introduce a novel method for representation learning that uses an\nartificial supervision signal based on counting visual primitives. This\nsupervision signal is obtained from an equivariance relation, which does not\nrequire any manual annotation. We relate transformations of images to\ntransformations of the representations. More specifically, we look for the\nrepresentation that satisfies such relation rather than the transformations\nthat match a given representation. In this paper, we use two image\ntransformations in the context of counting: scaling and tiling. The first\ntransformation exploits the fact that the number of visual primitives should be\ninvariant to scale. The second transformation allows us to equate the total\nnumber of visual primitives in each tile to that in the whole image. These two\ntransformations are combined in one constraint and used to train a neural\nnetwork with a contrastive loss. The proposed task produces representations\nthat perform on par or exceed the state of the art in transfer learning\nbenchmarks.","url_abs":"http://arxiv.org/abs/1708.06734v1","url_pdf":"http://arxiv.org/pdf/1708.06734v1.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":"representation-learning-by-learning-to-count","repo_url":"https://github.com/clvrai/representation-learning-by-learning-to-count","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"representation-learning-by-learning-to-count","repo_url":"https://github.com/gitlimlab/Representation-Learning-by-Learning-to-Count","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"Counting (AlexNet)","rank_in_archive_order":142,"of":144,"metrics":{"Number of Params":"61M","Top 1 Accuracy":"34.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.06734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.06734"}},"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/gitlimlab/Representation-Learning-by-Learning-to-Count","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clvrai/representation-learning-by-learning-to-count","reach":{"status":"unanswered"}}],"summary":{"ran_violates":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"3bd1e4d8ee61bea8","entry":"check_data_path","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3bd1e4d8ee61bea8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}