{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UOUHDLP4X4N7N6ZIDH6MG4H3PM","short_pith_number":"pith:UOUHDLP4","canonical_record":{"source":{"id":"1906.04950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-06-12T05:38:24Z","cross_cats_sorted":[],"title_canon_sha256":"f549e9f84156774e0f83e043c3a2e749e00fc8f196b399af605022aa4977b074","abstract_canon_sha256":"bbd53a7de10dfc742ec3e5ffc7902cbb1b293d80183d90f10c6ed81c9207d6a0"},"schema_version":"1.0"},"canonical_sha256":"a3a871adfcbf1bf6fb2819fcc370fb7b3aa47ee84de2256158bee71e20030ecd","source":{"kind":"arxiv","id":"1906.04950","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04950","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04950v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04950","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"UOUHDLP4X4N7","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UOUHDLP4X4N7N6ZI","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UOUHDLP4","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UOUHDLP4X4N7N6ZIDH6MG4H3PM","target":"record","payload":{"canonical_record":{"source":{"id":"1906.04950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-06-12T05:38:24Z","cross_cats_sorted":[],"title_canon_sha256":"f549e9f84156774e0f83e043c3a2e749e00fc8f196b399af605022aa4977b074","abstract_canon_sha256":"bbd53a7de10dfc742ec3e5ffc7902cbb1b293d80183d90f10c6ed81c9207d6a0"},"schema_version":"1.0"},"canonical_sha256":"a3a871adfcbf1bf6fb2819fcc370fb7b3aa47ee84de2256158bee71e20030ecd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:29.996174Z","signature_b64":"PW97+iux3a1VhuWosV7xhTuStmxJNYhVSoENMuuTbxKJiQOWtkF4M32TVJm8CfEjGCEKIFEnNs7eqbHtC2eQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a871adfcbf1bf6fb2819fcc370fb7b3aa47ee84de2256158bee71e20030ecd","last_reissued_at":"2026-05-17T23:43:29.995603Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:29.995603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.04950","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AuNLUztacsCXarJh9Hx1pxgBf8t2NpTeBws51fWBmskEdco/TQdkPX6iO17pHKxc33BVhQvhTf2DvXQnErK3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T04:37:15.383518Z"},"content_sha256":"0afcc4e6d3ecc4a1ebec12480684f0b798332bad267ce65625b9b1182e1ced70","schema_version":"1.0","event_id":"sha256:0afcc4e6d3ecc4a1ebec12480684f0b798332bad267ce65625b9b1182e1ced70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UOUHDLP4X4N7N6ZIDH6MG4H3PM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruizhe Cheng, Tianyi Fang, Xiangxi Mo","submitted_at":"2019-06-12T05:38:24Z","abstract_excerpt":"We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transfer learning methods typically face the trade-off between training time and accuracy. By adding \"attention module\" to each convolutional filters of the pre-trained network, we are able to rank and adjust the importance of each convolutional signal in an end-to-end pipeline. In this report, we show our method can adapt a pre-trianed ResNet50 for a fine-grained transfer learning task within few epochs and achieve accura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04950","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gs8+7RKcltUhz7FhQ0vjRz2dkl/ahoZMA5A1/lkNmWhD4LtCOWSTXmbqlp42LTTKFvxLSQAQlJv4Yd0Qzo6MAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T04:37:15.384049Z"},"content_sha256":"110abda28efc4ce7431ba78c192ef76769d14d84227dc1e461de555c6737513d","schema_version":"1.0","event_id":"sha256:110abda28efc4ce7431ba78c192ef76769d14d84227dc1e461de555c6737513d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOUHDLP4X4N7N6ZIDH6MG4H3PM/bundle.json","state_url":"https://pith.science/pith/UOUHDLP4X4N7N6ZIDH6MG4H3PM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOUHDLP4X4N7N6ZIDH6MG4H3PM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T04:37:15Z","links":{"resolver":"https://pith.science/pith/UOUHDLP4X4N7N6ZIDH6MG4H3PM","bundle":"https://pith.science/pith/UOUHDLP4X4N7N6ZIDH6MG4H3PM/bundle.json","state":"https://pith.science/pith/UOUHDLP4X4N7N6ZIDH6MG4H3PM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOUHDLP4X4N7N6ZIDH6MG4H3PM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UOUHDLP4X4N7N6ZIDH6MG4H3PM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bbd53a7de10dfc742ec3e5ffc7902cbb1b293d80183d90f10c6ed81c9207d6a0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-06-12T05:38:24Z","title_canon_sha256":"f549e9f84156774e0f83e043c3a2e749e00fc8f196b399af605022aa4977b074"},"schema_version":"1.0","source":{"id":"1906.04950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04950","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04950v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04950","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"UOUHDLP4X4N7","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UOUHDLP4X4N7N6ZI","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UOUHDLP4","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:110abda28efc4ce7431ba78c192ef76769d14d84227dc1e461de555c6737513d","target":"graph","created_at":"2026-05-17T23:43:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transfer learning methods typically face the trade-off between training time and accuracy. By adding \"attention module\" to each convolutional filters of the pre-trained network, we are able to rank and adjust the importance of each convolutional signal in an end-to-end pipeline. In this report, we show our method can adapt a pre-trianed ResNet50 for a fine-grained transfer learning task within few epochs and achieve accura","authors_text":"Ruizhe Cheng, Tianyi Fang, Xiangxi Mo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-06-12T05:38:24Z","title":"Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04950","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0afcc4e6d3ecc4a1ebec12480684f0b798332bad267ce65625b9b1182e1ced70","target":"record","created_at":"2026-05-17T23:43:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bbd53a7de10dfc742ec3e5ffc7902cbb1b293d80183d90f10c6ed81c9207d6a0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-06-12T05:38:24Z","title_canon_sha256":"f549e9f84156774e0f83e043c3a2e749e00fc8f196b399af605022aa4977b074"},"schema_version":"1.0","source":{"id":"1906.04950","kind":"arxiv","version":1}},"canonical_sha256":"a3a871adfcbf1bf6fb2819fcc370fb7b3aa47ee84de2256158bee71e20030ecd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a871adfcbf1bf6fb2819fcc370fb7b3aa47ee84de2256158bee71e20030ecd","first_computed_at":"2026-05-17T23:43:29.995603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:29.995603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PW97+iux3a1VhuWosV7xhTuStmxJNYhVSoENMuuTbxKJiQOWtkF4M32TVJm8CfEjGCEKIFEnNs7eqbHtC2eQDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:29.996174Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0afcc4e6d3ecc4a1ebec12480684f0b798332bad267ce65625b9b1182e1ced70","sha256:110abda28efc4ce7431ba78c192ef76769d14d84227dc1e461de555c6737513d"],"state_sha256":"24d664df31285e7fee12078ba580d154ff880b47ccb5a39302d654364e339c46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GMuwwl5WlKE6tEe/GBOHnJm4+s+HSznOOL+UUs0xdRBfrbNFDKmAdNo5EtDMdHxArWHd3trVMkY1wvqmra0uCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T04:37:15.385973Z","bundle_sha256":"dd1dc35c8c47ef29a85a8ab1dae2b513373b8b816a98e888e921c0c55c560eed"}}