{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SFKJH7LNSVQYOZJYBS4SMLVNHJ","short_pith_number":"pith:SFKJH7LN","schema_version":"1.0","canonical_sha256":"915493fd6d95618765380cb9262ead3a44517e2476413c643c27dd28c0e96649","source":{"kind":"arxiv","id":"1604.02426","version":3},"attestation_state":"computed","paper":{"title":"CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Filip Radenovi\\'c, Giorgos Tolias, Ond\\v{r}ej Chum","submitted_at":"2016-04-08T19:04:35Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positiv"},"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":"1604.02426","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-08T19:04:35Z","cross_cats_sorted":[],"title_canon_sha256":"93df4433cd90a35bd5307dbf6d68704a6d1d4a829198555a4f6dbb4362f2828e","abstract_canon_sha256":"11e7f3ea5aac588c375a61e3f2080b33f689bbe929483eebe058b0cd28c28af7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:05:12.453279Z","signature_b64":"5RuJtg1O//9f0ICKb8jpNljdZn7TE8UH/NZZN/eVxTxvzbYj+FoLlt5NoZ24wUlH7HhwftsFR9NOoc7IfAG8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"915493fd6d95618765380cb9262ead3a44517e2476413c643c27dd28c0e96649","last_reissued_at":"2026-05-18T01:05:12.452556Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:05:12.452556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Filip Radenovi\\'c, Giorgos Tolias, Ond\\v{r}ej Chum","submitted_at":"2016-04-08T19:04:35Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02426","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":""},"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":"1604.02426","created_at":"2026-05-18T01:05:12.452674+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.02426v3","created_at":"2026-05-18T01:05:12.452674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02426","created_at":"2026-05-18T01:05:12.452674+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFKJH7LNSVQY","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFKJH7LNSVQYOZJY","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFKJH7LN","created_at":"2026-05-18T12:30:44.179134+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/SFKJH7LNSVQYOZJYBS4SMLVNHJ","json":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ.json","graph_json":"https://pith.science/api/pith-number/SFKJH7LNSVQYOZJYBS4SMLVNHJ/graph.json","events_json":"https://pith.science/api/pith-number/SFKJH7LNSVQYOZJYBS4SMLVNHJ/events.json","paper":"https://pith.science/paper/SFKJH7LN"},"agent_actions":{"view_html":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ","download_json":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ.json","view_paper":"https://pith.science/paper/SFKJH7LN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.02426&json=true","fetch_graph":"https://pith.science/api/pith-number/SFKJH7LNSVQYOZJYBS4SMLVNHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SFKJH7LNSVQYOZJYBS4SMLVNHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ/action/storage_attestation","attest_author":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ/action/author_attestation","sign_citation":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ/action/citation_signature","submit_replication":"https://pith.science/pith/SFKJH7LNSVQYOZJYBS4SMLVNHJ/action/replication_record"}},"created_at":"2026-05-18T01:05:12.452674+00:00","updated_at":"2026-05-18T01:05:12.452674+00:00"}