{"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/when-deep-classifiers-agree-analyzing","title":"When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics","arxiv_id":"2105.08997","date":"2021-05-19","proceeding":null,"authors":["Iuliia Pliushch","Martin Mundt","Nicolas Lupp","Visvanathan Ramesh"],"abstract":"Although a plethora of architectural variants for deep classification has been introduced over time, recent works have found empirical evidence towards similarities in their training process. It has been hypothesized that neural networks converge not only to similar representations, but also exhibit a notion of empirical agreement on which data instances are learned first. Following in the latter works$'$ footsteps, we define a metric to quantify the relationship between such classification agreement over time, and posit that the agreement phenomenon can be mapped to core statistics of the investigated dataset. We empirically corroborate this hypothesis across the CIFAR10, Pascal, ImageNet and KTH-TIPS2 datasets. Our findings indicate that agreement seems to be independent of specific architectures, training hyper-parameters or labels, albeit follows an ordering according to image statistics.","url_abs":"https://arxiv.org/abs/2105.08997v2","url_pdf":"https://arxiv.org/pdf/2105.08997v2.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":"when-deep-classifiers-agree-analyzing","repo_url":"https://github.com/ccc-frankfurt/intrinsic_ordering_nn_training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.08997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08997"}},"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/ccc-frankfurt/intrinsic_ordering_nn_training","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"0accb4b755fadf1c","entry":"accuracy","repo":"ccc-frankfurt/intrinsic_ordering_nn_training","repo_kind":"official","path":"lib/helpers/accuracy_metrics.py","file_url":"https://github.com/ccc-frankfurt/intrinsic_ordering_nn_training/blob/HEAD/lib/helpers/accuracy_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0accb4b755fadf1c"}},{"code_sha256_prefix":"91312041642f4afe","entry":"calc_gpu_mem_req","repo":"ccc-frankfurt/intrinsic_ordering_nn_training","repo_kind":"official","path":"lib/architectures.py","file_url":"https://github.com/ccc-frankfurt/intrinsic_ordering_nn_training/blob/HEAD/lib/architectures.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91312041642f4afe"}},{"code_sha256_prefix":"2722de6c59374643","entry":"dct","repo":"ccc-frankfurt/intrinsic_ordering_nn_training","repo_kind":"official","path":"lib/helpers/dct.py","file_url":"https://github.com/ccc-frankfurt/intrinsic_ordering_nn_training/blob/HEAD/lib/helpers/dct.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2722de6c59374643"}},{"code_sha256_prefix":"c3f2ecb9e39faba4","entry":"dct1","repo":"ccc-frankfurt/intrinsic_ordering_nn_training","repo_kind":"official","path":"lib/helpers/dct.py","file_url":"https://github.com/ccc-frankfurt/intrinsic_ordering_nn_training/blob/HEAD/lib/helpers/dct.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3f2ecb9e39faba4"}},{"code_sha256_prefix":"0692e20b6c3a5db8","entry":"get_feat_size","repo":"ccc-frankfurt/intrinsic_ordering_nn_training","repo_kind":"official","path":"lib/architectures.py","file_url":"https://github.com/ccc-frankfurt/intrinsic_ordering_nn_training/blob/HEAD/lib/architectures.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0692e20b6c3a5db8"}},{"code_sha256_prefix":"e2f1e6b54f8342d0","entry":"idct1","repo":"ccc-frankfurt/intrinsic_ordering_nn_training","repo_kind":"official","path":"lib/helpers/dct.py","file_url":"https://github.com/ccc-frankfurt/intrinsic_ordering_nn_training/blob/HEAD/lib/helpers/dct.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2f1e6b54f8342d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}