{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQ4S5R62Z6X4FJOTLMW5DIRBN3","short_pith_number":"pith:DQ4S5R62","schema_version":"1.0","canonical_sha256":"1c392ec7dacfafc2a5d35b2dd1a2216ef8a1149bdc1e7874631c32e5d977d318","source":{"kind":"arxiv","id":"2402.15172","version":1},"attestation_state":"computed","paper":{"title":"Attention-Guided Masked Autoencoders For Learning Image Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dominik Engel, Leon Sick, Pedro Hermosilla, Timo Ropinski","submitted_at":"2024-02-23T08:11:25Z","abstract_excerpt":"Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to inform the reconstruction process through an attention-guided loss function. By leveraging advances in unsupervised object discovery, we obtain an attention map of the scene which we employ in the loss function to put increased emphasis on reconstructing relevant objects, thus effectively incentivizing the model to learn more object-focused representations wit"},"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":"2402.15172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-23T08:11:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"49cef3a9ccaf3deab36efb9675e3717170d398e69ce613e1c0cbf1e40e53994f","abstract_canon_sha256":"8bf71152eae40d9a0b5eb326e9cc89a8b329782257e8d763ac70b100ac31922d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:36.695505Z","signature_b64":"MyTXDyzUYDF46vbGXrVarQlFitUOzpO5w/33aR4OhwEWqXcuhLWQV7chnC6xhR1YXufFsW1oHP4XT6lI5hcyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c392ec7dacfafc2a5d35b2dd1a2216ef8a1149bdc1e7874631c32e5d977d318","last_reissued_at":"2026-07-05T07:48:36.695034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:36.695034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-Guided Masked Autoencoders For Learning Image Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dominik Engel, Leon Sick, Pedro Hermosilla, Timo Ropinski","submitted_at":"2024-02-23T08:11:25Z","abstract_excerpt":"Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to inform the reconstruction process through an attention-guided loss function. By leveraging advances in unsupervised object discovery, we obtain an attention map of the scene which we employ in the loss function to put increased emphasis on reconstructing relevant objects, thus effectively incentivizing the model to learn more object-focused representations wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15172","kind":"arxiv","version":1},"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/2402.15172/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":"2402.15172","created_at":"2026-07-05T07:48:36.695088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15172v1","created_at":"2026-07-05T07:48:36.695088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15172","created_at":"2026-07-05T07:48:36.695088+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQ4S5R62Z6X4","created_at":"2026-07-05T07:48:36.695088+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQ4S5R62Z6X4FJOT","created_at":"2026-07-05T07:48:36.695088+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQ4S5R62","created_at":"2026-07-05T07:48:36.695088+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/DQ4S5R62Z6X4FJOTLMW5DIRBN3","json":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3.json","graph_json":"https://pith.science/api/pith-number/DQ4S5R62Z6X4FJOTLMW5DIRBN3/graph.json","events_json":"https://pith.science/api/pith-number/DQ4S5R62Z6X4FJOTLMW5DIRBN3/events.json","paper":"https://pith.science/paper/DQ4S5R62"},"agent_actions":{"view_html":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3","download_json":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3.json","view_paper":"https://pith.science/paper/DQ4S5R62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15172&json=true","fetch_graph":"https://pith.science/api/pith-number/DQ4S5R62Z6X4FJOTLMW5DIRBN3/graph.json","fetch_events":"https://pith.science/api/pith-number/DQ4S5R62Z6X4FJOTLMW5DIRBN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3/action/storage_attestation","attest_author":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3/action/author_attestation","sign_citation":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3/action/citation_signature","submit_replication":"https://pith.science/pith/DQ4S5R62Z6X4FJOTLMW5DIRBN3/action/replication_record"}},"created_at":"2026-07-05T07:48:36.695088+00:00","updated_at":"2026-07-05T07:48:36.695088+00:00"}