{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IEG2IAT3AVT2CM4LTW3E3RR2FD","short_pith_number":"pith:IEG2IAT3","schema_version":"1.0","canonical_sha256":"410da4027b0567a1338b9db64dc63a28f046bfc87a59d1b959ac3660f4953ea7","source":{"kind":"arxiv","id":"1611.05503","version":1},"attestation_state":"computed","paper":{"title":"On the Exploration of Convolutional Fusion Networks for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael S. Lew, Yanming Guo, Yu Liu","submitted_at":"2016-11-16T23:33:38Z","abstract_excerpt":"Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules. Hence, we propose an efficient approach to fuse multi-scale deep representations, called convolutional fusion networks (CFN). Owing to using 1$\\times$1 convolution and global average pooling, CFN can efficiently generate the side branches while adding few parameters. In addition, we present a locally-connected fusion module, which can learn adaptive weights for the side branches and form a discriminatively fused feature. CFN models trained on the CIFAR "},"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":"1611.05503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-16T23:33:38Z","cross_cats_sorted":[],"title_canon_sha256":"12a129b9b775068789fc1614f86618681b9ca2cee40312b9421318db8ac64c0c","abstract_canon_sha256":"fa99d77d21e93bcee943756c7558311c05f852b6c1974e534313e9753161a9fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:03.371136Z","signature_b64":"VphJR4U9k6YZkd2malYrujmBLEWOvk5S8ok8E456+HA6GmVwNMyOLzkKlXm+QQZAbshHYXyCkzria0MfHJwCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"410da4027b0567a1338b9db64dc63a28f046bfc87a59d1b959ac3660f4953ea7","last_reissued_at":"2026-05-18T00:58:03.370373Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:03.370373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Exploration of Convolutional Fusion Networks for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael S. Lew, Yanming Guo, Yu Liu","submitted_at":"2016-11-16T23:33:38Z","abstract_excerpt":"Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules. Hence, we propose an efficient approach to fuse multi-scale deep representations, called convolutional fusion networks (CFN). Owing to using 1$\\times$1 convolution and global average pooling, CFN can efficiently generate the side branches while adding few parameters. In addition, we present a locally-connected fusion module, which can learn adaptive weights for the side branches and form a discriminatively fused feature. CFN models trained on the CIFAR "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05503","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1611.05503","created_at":"2026-05-18T00:58:03.370500+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05503v1","created_at":"2026-05-18T00:58:03.370500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05503","created_at":"2026-05-18T00:58:03.370500+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEG2IAT3AVT2","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEG2IAT3AVT2CM4L","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEG2IAT3","created_at":"2026-05-18T12:30:22.444734+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/IEG2IAT3AVT2CM4LTW3E3RR2FD","json":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD.json","graph_json":"https://pith.science/api/pith-number/IEG2IAT3AVT2CM4LTW3E3RR2FD/graph.json","events_json":"https://pith.science/api/pith-number/IEG2IAT3AVT2CM4LTW3E3RR2FD/events.json","paper":"https://pith.science/paper/IEG2IAT3"},"agent_actions":{"view_html":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD","download_json":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD.json","view_paper":"https://pith.science/paper/IEG2IAT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05503&json=true","fetch_graph":"https://pith.science/api/pith-number/IEG2IAT3AVT2CM4LTW3E3RR2FD/graph.json","fetch_events":"https://pith.science/api/pith-number/IEG2IAT3AVT2CM4LTW3E3RR2FD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD/action/storage_attestation","attest_author":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD/action/author_attestation","sign_citation":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD/action/citation_signature","submit_replication":"https://pith.science/pith/IEG2IAT3AVT2CM4LTW3E3RR2FD/action/replication_record"}},"created_at":"2026-05-18T00:58:03.370500+00:00","updated_at":"2026-05-18T00:58:03.370500+00:00"}