{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XPUIAWJYKDCL3VZ7AEJVG6BF7F","short_pith_number":"pith:XPUIAWJY","schema_version":"1.0","canonical_sha256":"bbe880593850c4bdd73f0113537825f96dd09e59be41aaba75562bf66c2a41d9","source":{"kind":"arxiv","id":"2011.05499","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Learning of Dense Visual Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Amjad Almahairi, Florian Golemo, Pedro O. Pinheiro, Ryan Y. Benmalek","submitted_at":"2020-11-11T01:28:11Z","abstract_excerpt":"Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewi"},"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":"2011.05499","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-11T01:28:11Z","cross_cats_sorted":[],"title_canon_sha256":"410d9fcf95fe8881eac4a8175f988d21cbe882c9fff9374164c79df9249778c2","abstract_canon_sha256":"4cd62ba39c04c2411788abbeb8afeca7e3112ad7213babd9a26e952ec2b452cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:36.586560Z","signature_b64":"ljO3DnCtP3YGr3GdzNRhKFOf3rFLvdPQvVvRCxkEh8PGjNptDwRvFXPYtPFG46L8jE8wPv76t+MJAxttpnnaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe880593850c4bdd73f0113537825f96dd09e59be41aaba75562bf66c2a41d9","last_reissued_at":"2026-07-05T01:57:36.586081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:36.586081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Learning of Dense Visual Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Amjad Almahairi, Florian Golemo, Pedro O. Pinheiro, Ryan Y. Benmalek","submitted_at":"2020-11-11T01:28:11Z","abstract_excerpt":"Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05499","kind":"arxiv","version":2},"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/2011.05499/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":"2011.05499","created_at":"2026-07-05T01:57:36.586137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05499v2","created_at":"2026-07-05T01:57:36.586137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05499","created_at":"2026-07-05T01:57:36.586137+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPUIAWJYKDCL","created_at":"2026-07-05T01:57:36.586137+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPUIAWJYKDCL3VZ7","created_at":"2026-07-05T01:57:36.586137+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPUIAWJY","created_at":"2026-07-05T01:57:36.586137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19242","citing_title":"Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F","json":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F.json","graph_json":"https://pith.science/api/pith-number/XPUIAWJYKDCL3VZ7AEJVG6BF7F/graph.json","events_json":"https://pith.science/api/pith-number/XPUIAWJYKDCL3VZ7AEJVG6BF7F/events.json","paper":"https://pith.science/paper/XPUIAWJY"},"agent_actions":{"view_html":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F","download_json":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F.json","view_paper":"https://pith.science/paper/XPUIAWJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05499&json=true","fetch_graph":"https://pith.science/api/pith-number/XPUIAWJYKDCL3VZ7AEJVG6BF7F/graph.json","fetch_events":"https://pith.science/api/pith-number/XPUIAWJYKDCL3VZ7AEJVG6BF7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/action/storage_attestation","attest_author":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/action/author_attestation","sign_citation":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/action/citation_signature","submit_replication":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/action/replication_record"}},"created_at":"2026-07-05T01:57:36.586137+00:00","updated_at":"2026-07-05T01:57:36.586137+00:00"}