{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3F255MUAHHLEBFDS2IZURVSIUI","short_pith_number":"pith:3F255MUA","schema_version":"1.0","canonical_sha256":"d975deb28039d6409472d23348d648a23c63a941f553ec4c9b9929595cb78aba","source":{"kind":"arxiv","id":"1905.03540","version":4},"attestation_state":"computed","paper":{"title":"Embedding Human Knowledge into Deep Neural Network via Attention Map","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hironobu Fujiyoshi, Hiroshi Fukui, Masahiro Mitsuhara, Takanori Ogata, Takayoshi Yamashita, Tsubasa Hirakawa, Yusuke Sakashita","submitted_at":"2019-05-09T11:32:44Z","abstract_excerpt":"In this work, we aim to realize a method for embedding human knowledge into deep neural networks. While the conventional method to embed human knowledge has been applied for non-deep machine learning, it is challenging to apply it for deep learning models due to the enormous number of model parameters. To tackle this problem, we focus on the attention mechanism of an attention branch network (ABN). In this paper, we propose a fine-tuning method that utilizes a single-channel attention map which is manually edited by a human expert. Our fine-tuning method can train a network so that the output "},"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":"1905.03540","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T11:32:44Z","cross_cats_sorted":[],"title_canon_sha256":"7782bf9cc4f7e199d58da03cd3df006a785bd7a13ea18f51b9a0b9ba7a121e54","abstract_canon_sha256":"5aa8179139be1066c052bfa8c06ceb02c67bac7da53554f466050a42dc70543a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:16.763326Z","signature_b64":"fz6ZbPnp7/wG6ksfmiLxt2yuz7KyiyVQFlcNLhWSK8EehM2wp1C9R4NjMnCJDwevHvC1tXhsUeUm0wjaRxZXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d975deb28039d6409472d23348d648a23c63a941f553ec4c9b9929595cb78aba","last_reissued_at":"2026-07-05T00:27:16.762865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:16.762865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedding Human Knowledge into Deep Neural Network via Attention Map","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hironobu Fujiyoshi, Hiroshi Fukui, Masahiro Mitsuhara, Takanori Ogata, Takayoshi Yamashita, Tsubasa Hirakawa, Yusuke Sakashita","submitted_at":"2019-05-09T11:32:44Z","abstract_excerpt":"In this work, we aim to realize a method for embedding human knowledge into deep neural networks. While the conventional method to embed human knowledge has been applied for non-deep machine learning, it is challenging to apply it for deep learning models due to the enormous number of model parameters. To tackle this problem, we focus on the attention mechanism of an attention branch network (ABN). In this paper, we propose a fine-tuning method that utilizes a single-channel attention map which is manually edited by a human expert. Our fine-tuning method can train a network so that the output "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03540","kind":"arxiv","version":4},"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/1905.03540/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":"1905.03540","created_at":"2026-07-05T00:27:16.762916+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03540v4","created_at":"2026-07-05T00:27:16.762916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03540","created_at":"2026-07-05T00:27:16.762916+00:00"},{"alias_kind":"pith_short_12","alias_value":"3F255MUAHHLE","created_at":"2026-07-05T00:27:16.762916+00:00"},{"alias_kind":"pith_short_16","alias_value":"3F255MUAHHLEBFDS","created_at":"2026-07-05T00:27:16.762916+00:00"},{"alias_kind":"pith_short_8","alias_value":"3F255MUA","created_at":"2026-07-05T00:27:16.762916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07451","citing_title":"TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment","ref_index":209,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI","json":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI.json","graph_json":"https://pith.science/api/pith-number/3F255MUAHHLEBFDS2IZURVSIUI/graph.json","events_json":"https://pith.science/api/pith-number/3F255MUAHHLEBFDS2IZURVSIUI/events.json","paper":"https://pith.science/paper/3F255MUA"},"agent_actions":{"view_html":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI","download_json":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI.json","view_paper":"https://pith.science/paper/3F255MUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03540&json=true","fetch_graph":"https://pith.science/api/pith-number/3F255MUAHHLEBFDS2IZURVSIUI/graph.json","fetch_events":"https://pith.science/api/pith-number/3F255MUAHHLEBFDS2IZURVSIUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI/action/storage_attestation","attest_author":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI/action/author_attestation","sign_citation":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI/action/citation_signature","submit_replication":"https://pith.science/pith/3F255MUAHHLEBFDS2IZURVSIUI/action/replication_record"}},"created_at":"2026-07-05T00:27:16.762916+00:00","updated_at":"2026-07-05T00:27:16.762916+00:00"}