{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YNA677RU5MJQYHS2QGNX2NGSS3","short_pith_number":"pith:YNA677RU","schema_version":"1.0","canonical_sha256":"c341effe34eb130c1e5a819b7d34d296e401a4c87c89c843d0f45cc563fef9b9","source":{"kind":"arxiv","id":"1802.05394","version":2},"attestation_state":"computed","paper":{"title":"Cost-Effective Training of Deep CNNs with Active Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jia-Wei Zhao, Sheng-Jun Huang, Zhao-Yang Liu","submitted_at":"2018-02-15T03:06:06Z","abstract_excerpt":"Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the network architecture, repeated trial-and-error process to tune the parameters, and a large set of labeled data to train the model. In this paper, we propose to overcome these challenges by actively adapting a pre-trained model to a new task with less labeled examples. Specifically, the pre-trained model is iteratively fine tuned based on the most useful example"},"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":"1802.05394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-15T03:06:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"73fe22501435882f1501db862b47b2d6ad4a6b6f15fd0266f75fa4a9e34b4d16","abstract_canon_sha256":"3b3e4e141b188c95cb6169edd75c509521880273484968e2d0f3acab70c5b7b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:14.011547Z","signature_b64":"UG3LSaxQA/WD98uCHsll9I59Zl4XdipEa7IISw47I92troioXOZQNfZArn5BCgEcSP+cBn4wBQe0dnyqZ6FMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c341effe34eb130c1e5a819b7d34d296e401a4c87c89c843d0f45cc563fef9b9","last_reissued_at":"2026-05-18T00:14:14.010733Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:14.010733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cost-Effective Training of Deep CNNs with Active Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jia-Wei Zhao, Sheng-Jun Huang, Zhao-Yang Liu","submitted_at":"2018-02-15T03:06:06Z","abstract_excerpt":"Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the network architecture, repeated trial-and-error process to tune the parameters, and a large set of labeled data to train the model. In this paper, we propose to overcome these challenges by actively adapting a pre-trained model to a new task with less labeled examples. Specifically, the pre-trained model is iteratively fine tuned based on the most useful example"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05394","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":""},"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":"1802.05394","created_at":"2026-05-18T00:14:14.010861+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05394v2","created_at":"2026-05-18T00:14:14.010861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05394","created_at":"2026-05-18T00:14:14.010861+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNA677RU5MJQ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNA677RU5MJQYHS2","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNA677RU","created_at":"2026-05-18T12:33:04.347982+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/YNA677RU5MJQYHS2QGNX2NGSS3","json":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3.json","graph_json":"https://pith.science/api/pith-number/YNA677RU5MJQYHS2QGNX2NGSS3/graph.json","events_json":"https://pith.science/api/pith-number/YNA677RU5MJQYHS2QGNX2NGSS3/events.json","paper":"https://pith.science/paper/YNA677RU"},"agent_actions":{"view_html":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3","download_json":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3.json","view_paper":"https://pith.science/paper/YNA677RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05394&json=true","fetch_graph":"https://pith.science/api/pith-number/YNA677RU5MJQYHS2QGNX2NGSS3/graph.json","fetch_events":"https://pith.science/api/pith-number/YNA677RU5MJQYHS2QGNX2NGSS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3/action/storage_attestation","attest_author":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3/action/author_attestation","sign_citation":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3/action/citation_signature","submit_replication":"https://pith.science/pith/YNA677RU5MJQYHS2QGNX2NGSS3/action/replication_record"}},"created_at":"2026-05-18T00:14:14.010861+00:00","updated_at":"2026-05-18T00:14:14.010861+00:00"}