{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KCYFWUPXQVNXFEEKSKUCS47LSN","short_pith_number":"pith:KCYFWUPX","schema_version":"1.0","canonical_sha256":"50b05b51f7855b72908a92a82973eb937048f2038f17359eaa0fd7c9293f6490","source":{"kind":"arxiv","id":"2011.01901","version":3},"attestation_state":"computed","paper":{"title":"Learning Visual Representations for Transfer Learning by Suppressing Texture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Abhishek Sharma, Ankan Bansal, Anshul Shah, David Jacobs, Janit Anjaria, Jonghyun Choi, Shlok Mishra","submitted_at":"2020-11-03T18:27:03Z","abstract_excerpt":"Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information. In self-supervised learning in particular, texture as a low-level cue may provide shortcuts that prevent the network from learning higher level representations. To address these problems we propose to use classic methods based on anisotropic diffusion to augment training using images with suppressed texture. This simple method helps retain important edge information and suppress texture at the same time. We empirically show that our method "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.01901","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-03T18:27:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41bbdefba793d487efe71c0c596f63076ff113287c58f119fbdf8ae34c60adc6","abstract_canon_sha256":"9865d4db8bf67882e6961d1d8d01444e749e79b644a9a82f5f6f510f4857b73d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:14.131495Z","signature_b64":"swOEwegdS8F2/F7m/mJiHZDlEJ596wfkIQTNwFgYxTCam28dTSrNRpfsDUMPTfahbzkqaA1qw8rl6JYumrN7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50b05b51f7855b72908a92a82973eb937048f2038f17359eaa0fd7c9293f6490","last_reissued_at":"2026-07-05T05:36:14.131019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:14.131019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Visual Representations for Transfer Learning by Suppressing Texture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Abhishek Sharma, Ankan Bansal, Anshul Shah, David Jacobs, Janit Anjaria, Jonghyun Choi, Shlok Mishra","submitted_at":"2020-11-03T18:27:03Z","abstract_excerpt":"Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information. In self-supervised learning in particular, texture as a low-level cue may provide shortcuts that prevent the network from learning higher level representations. To address these problems we propose to use classic methods based on anisotropic diffusion to augment training using images with suppressed texture. This simple method helps retain important edge information and suppress texture at the same time. We empirically show that our method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01901","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.01901/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.01901","created_at":"2026-07-05T05:36:14.131085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01901v3","created_at":"2026-07-05T05:36:14.131085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01901","created_at":"2026-07-05T05:36:14.131085+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCYFWUPXQVNX","created_at":"2026-07-05T05:36:14.131085+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCYFWUPXQVNXFEEK","created_at":"2026-07-05T05:36:14.131085+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCYFWUPX","created_at":"2026-07-05T05:36:14.131085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN","json":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN.json","graph_json":"https://pith.science/api/pith-number/KCYFWUPXQVNXFEEKSKUCS47LSN/graph.json","events_json":"https://pith.science/api/pith-number/KCYFWUPXQVNXFEEKSKUCS47LSN/events.json","paper":"https://pith.science/paper/KCYFWUPX"},"agent_actions":{"view_html":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN","download_json":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN.json","view_paper":"https://pith.science/paper/KCYFWUPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01901&json=true","fetch_graph":"https://pith.science/api/pith-number/KCYFWUPXQVNXFEEKSKUCS47LSN/graph.json","fetch_events":"https://pith.science/api/pith-number/KCYFWUPXQVNXFEEKSKUCS47LSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN/action/storage_attestation","attest_author":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN/action/author_attestation","sign_citation":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN/action/citation_signature","submit_replication":"https://pith.science/pith/KCYFWUPXQVNXFEEKSKUCS47LSN/action/replication_record"}},"created_at":"2026-07-05T05:36:14.131085+00:00","updated_at":"2026-07-05T05:36:14.131085+00:00"}