{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:M6GY76FXZJJSJR4IZR5PKQ2C63","short_pith_number":"pith:M6GY76FX","schema_version":"1.0","canonical_sha256":"678d8ff8b7ca5324c788cc7af54342f6c5a2f035ad83e57b3a1b261859712773","source":{"kind":"arxiv","id":"1807.06521","version":2},"attestation_state":"computed","paper":{"title":"CBAM: Convolutional Block Attention Module","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"In So Kweon, Jongchan Park, Joon-Young Lee, Sanghyun Woo","submitted_at":"2018-07-17T16:05:59Z","abstract_excerpt":"We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive ex"},"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":"1807.06521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-17T16:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"a76faa37edb4d91953a9d310a95b52b166bb2c3c2f1074a9ed12296b8641dbd5","abstract_canon_sha256":"439fa1b6d3d718085945d8e8a733c11dbf5ad03f37be0009d205aa7f9efe5304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:27.481953Z","signature_b64":"LHQiUlngHGYbefwUD9tfhYTQ2rAvK/th2hmSdbxpaW+lmAG4Yxu+D2xiwaWyhlJHTuIDIMthqfgoB6vc5ohlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"678d8ff8b7ca5324c788cc7af54342f6c5a2f035ad83e57b3a1b261859712773","last_reissued_at":"2026-05-18T00:10:27.481431Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:27.481431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CBAM: Convolutional Block Attention Module","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"In So Kweon, Jongchan Park, Joon-Young Lee, Sanghyun Woo","submitted_at":"2018-07-17T16:05:59Z","abstract_excerpt":"We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06521","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":"1807.06521","created_at":"2026-05-18T00:10:27.481521+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06521v2","created_at":"2026-05-18T00:10:27.481521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06521","created_at":"2026-05-18T00:10:27.481521+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6GY76FXZJJS","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6GY76FXZJJSJR4I","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6GY76FX","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.06838","citing_title":"Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14255","citing_title":"Architecture-Aware Explanation Auditing for Industrial Visual Inspection","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14255","citing_title":"Architecture-Aware Explanation Auditing for Industrial Visual Inspection","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06678","citing_title":"A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63","json":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63.json","graph_json":"https://pith.science/api/pith-number/M6GY76FXZJJSJR4IZR5PKQ2C63/graph.json","events_json":"https://pith.science/api/pith-number/M6GY76FXZJJSJR4IZR5PKQ2C63/events.json","paper":"https://pith.science/paper/M6GY76FX"},"agent_actions":{"view_html":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63","download_json":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63.json","view_paper":"https://pith.science/paper/M6GY76FX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06521&json=true","fetch_graph":"https://pith.science/api/pith-number/M6GY76FXZJJSJR4IZR5PKQ2C63/graph.json","fetch_events":"https://pith.science/api/pith-number/M6GY76FXZJJSJR4IZR5PKQ2C63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63/action/storage_attestation","attest_author":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63/action/author_attestation","sign_citation":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63/action/citation_signature","submit_replication":"https://pith.science/pith/M6GY76FXZJJSJR4IZR5PKQ2C63/action/replication_record"}},"created_at":"2026-05-18T00:10:27.481521+00:00","updated_at":"2026-05-18T00:10:27.481521+00:00"}