{"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/demystifying-self-supervised-learning-an","title":"Self-supervised Learning from a Multi-view Perspective","arxiv_id":"2006.05576","date":"2020-06-10","proceeding":"ICLR 2021 1","authors":["Yao-Hung Hubert Tsai","Yue Wu","Ruslan Salakhutdinov","Louis-Philippe Morency"],"abstract":"As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning. Many proposed approaches for self-supervised learning follow naturally a multi-view perspective, where the input (e.g., original images) and the self-supervised signals (e.g., augmented images) can be seen as two redundant views of the data. Building from this multi-view perspective, this paper provides an information-theoretical framework to better understand the properties that encourage successful self-supervised learning. Specifically, we demonstrate that self-supervised learned representations can extract task-relevant information and discard task-irrelevant information. Our theoretical framework paves the way to a larger space of self-supervised learning objective design. In particular, we propose a composite objective that bridges the gap between prior contrastive and predictive learning objectives, and introduce an additional objective term to discard task-irrelevant information. To verify our analysis, we conduct controlled experiments to evaluate the impact of the composite objectives. We also explore our framework's empirical generalization beyond the multi-view perspective, where the cross-view redundancy may not be clearly observed.","url_abs":"https://arxiv.org/abs/2006.05576v4","url_pdf":"https://arxiv.org/pdf/2006.05576v4.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":"demystifying-self-supervised-learning-an","repo_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.05576","atlas_url":"https://app.syntology.ai/?focus=2006.05576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05576"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.05576"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.05576"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.05576\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2006.05576"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.05576\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.05576"},"call":"get_concepts_for_paper(arxiv_id=\"2006.05576\")"}],"by_repo":[{"repo":"yaohungt/Demystifying_Self_Supervised_Learning","kind":"official","samples":15,"ran":11,"instrument":1,"unverified":4}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2006.05576.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2006.05576.svg"},"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/yaohungt/Demystifying_Self_Supervised_Learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":10,"ran_draft_wrong":1,"unverified":4},"n_samples":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":15,"ran":11,"n_ran_checked":10,"n_instrument":1,"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":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":1,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":11,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"0a7d9a94b7082769","code_sha256_prefix":"0a7d9a94b7082769","entry":"AE_loss","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"Omniglot/compute_MI_CondEntro.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/Omniglot/compute_MI_CondEntro.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:Tensor/2/float, s:Tensor/2/float, encoder:callable/0/?, decoder:callable/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0a7d9a94b7082769"}},{"code_sha256":"2e338c4bb3d62d7e","code_sha256_prefix":"2e338c4bb3d62d7e","entry":"add_inv_pred_loss","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/objective.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"repres:SymbolicTensor/2/float, inv_pred_coeff:float/0/float, weights:float/0/float","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2e338c4bb3d62d7e"}},{"code_sha256":"8af989f02c354e14","code_sha256_prefix":"8af989f02c354e14","entry":"add_supervised_loss","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/objective.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"labels:SymbolicTensor/2/float, logits:SymbolicTensor/2/float, weights:SymbolicTensor/1/float","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8af989f02c354e14"}},{"code_sha256":"324c58e9994efed0","code_sha256_prefix":"324c58e9994efed0","entry":"color_jitter","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/data_util.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/data_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:SymbolicTensor/3/float, strength:float/0/float, random_order:bool/0/bool","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"324c58e9994efed0"}},{"code_sha256":"7ce61f1a25809b6d","code_sha256_prefix":"7ce61f1a25809b6d","entry":"dropblock","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/resnet.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"net:SymbolicTensor/4/float, is_training:bool/0/bool, keep_prob:float/0/float, dropblock_size:int/0/int, data_format:str/0/str","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7ce61f1a25809b6d"}},{"code_sha256":"3223825e26df85e7","code_sha256_prefix":"3223825e26df85e7","entry":"fixed_padding","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/resnet.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"inputs:SymbolicTensor/4/float, kernel_size:int/0/int, data_format:str/0/str","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":"/code/fixed-padding","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3223825e26df85e7"}},{"code_sha256":"1eed2bc576d1a00a","code_sha256_prefix":"1eed2bc576d1a00a","entry":"init_models","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"Omniglot/compute_MI_CondEntro.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/Omniglot/compute_MI_CondEntro.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"stage:str/0/str, additional_encoder:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1eed2bc576d1a00a"}},{"code_sha256":"b509a54eb5ec250b","code_sha256_prefix":"b509a54eb5ec250b","entry":"mlp","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"Omniglot/compute_MI_CondEntro.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/Omniglot/compute_MI_CondEntro.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dim:int/0/int, hidden_dim:int/0/int, output_dim:int/0/int, layers:int/0/int, batch_norm:bool/0/bool","fixture_out_type":"Sequential","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":"/code/mlp-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b509a54eb5ec250b"}},{"code_sha256":"0c26c80b6286f5ec","code_sha256_prefix":"0c26c80b6286f5ec","entry":"pad_to_batch","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/data.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dataset:DatasetV1Adapter/0/?, batch_size:int/0/int","fixture_out_type":"DatasetV1Adapter","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0c26c80b6286f5ec"}},{"code_sha256":"d04f187058cb2a9c","code_sha256_prefix":"d04f187058cb2a9c","entry":"random_apply","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/data_util.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/data_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"func:callable/0/?, p:float/0/float, x:SymbolicTensor/1/float","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":"/code/random-apply","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d04f187058cb2a9c"}},{"code_sha256":"7aac0de5d1568953","code_sha256_prefix":"7aac0de5d1568953","entry":"tpu_cross_replica_concat","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/objective.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/objective.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tensor:SymbolicTensor/2/float, tpu_context:TPUContext/0/?","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7aac0de5d1568953"}},{"code_sha256":"14ec8ff095316493","code_sha256_prefix":"14ec8ff095316493","entry":"get_train_steps","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/model_util.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/model_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-train-steps","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"14ec8ff095316493"}},{"code_sha256":"fb45bd9f63767265","code_sha256_prefix":"fb45bd9f63767265","entry":"learning_rate_schedule","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/model_util.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/model_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/learning-rate-schedule","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fb45bd9f63767265"}},{"code_sha256":"49c827442d2fb761","code_sha256_prefix":"49c827442d2fb761","entry":"to_grayscale","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"CIFAR10/data_util.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/CIFAR10/data_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/to-grayscale","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"49c827442d2fb761"}},{"code_sha256":"667eaf3785a1c4a9","code_sha256_prefix":"667eaf3785a1c4a9","entry":"train_val","repo":"yaohungt/Demystifying_Self_Supervised_Learning","repo_kind":"official","path":"Omniglot/linear.py","file_url":"https://github.com/yaohungt/Demystifying_Self_Supervised_Learning/blob/HEAD/Omniglot/linear.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/train-val","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from leftthomas/SimCLR, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"667eaf3785a1c4a9"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1f653f629dc750479e35aa011b8b23353da222f0665713dd3bf9e92991f68673","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}