{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NEIZSLNDOYE7DSQCX5RCR54A5I","short_pith_number":"pith:NEIZSLND","schema_version":"1.0","canonical_sha256":"6911992da37609f1ca02bf6228f780ea0c1afb839e51ac50beb9400829fb8462","source":{"kind":"arxiv","id":"2104.14124","version":1},"attestation_state":"computed","paper":{"title":"Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.CV","authors_text":"Dongchao Wen, Hongxing Gao, Junjie Liu, Kinya Osa, Masami Kato, Motoki Yoshinaga, Tse-Wei Chen, Wei Tao","submitted_at":"2021-04-29T05:44:02Z","abstract_excerpt":"\"Lightweight convolutional neural networks\" is an important research topic in the field of embedded vision. To implement image recognition tasks on a resource-limited hardware platform, it is necessary to reduce the memory size and the computational cost. The contribution of this paper is stated as follows. First, we propose an algorithm to process a specific network architecture (Condensation-Net) without increasing the maximum memory storage for feature maps. The architecture for virtual feature maps saves 26.5% of memory bandwidth by calculating the results of cross-channel pooling before s"},"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":"2104.14124","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-29T05:44:02Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"58be0436a80ebf5b86eb5204893afb4b40613259609059a9ec80e521659bd3c0","abstract_canon_sha256":"9e494b6016f8b83f451df93e4e03bfc86e3818e0a0aed0ccd69190d1987513ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:13.327881Z","signature_b64":"PMHybhjmNY+Hg+mkfCEzFCYkrEfWMibP+pp0YVXebxYVOE31ao1zSU2/cUkD+uj/aZN/QvyuCfLvcmG3O5OyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6911992da37609f1ca02bf6228f780ea0c1afb839e51ac50beb9400829fb8462","last_reissued_at":"2026-07-05T02:36:13.327448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:13.327448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.CV","authors_text":"Dongchao Wen, Hongxing Gao, Junjie Liu, Kinya Osa, Masami Kato, Motoki Yoshinaga, Tse-Wei Chen, Wei Tao","submitted_at":"2021-04-29T05:44:02Z","abstract_excerpt":"\"Lightweight convolutional neural networks\" is an important research topic in the field of embedded vision. To implement image recognition tasks on a resource-limited hardware platform, it is necessary to reduce the memory size and the computational cost. The contribution of this paper is stated as follows. First, we propose an algorithm to process a specific network architecture (Condensation-Net) without increasing the maximum memory storage for feature maps. The architecture for virtual feature maps saves 26.5% of memory bandwidth by calculating the results of cross-channel pooling before s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14124","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.14124/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":"2104.14124","created_at":"2026-07-05T02:36:13.327508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.14124v1","created_at":"2026-07-05T02:36:13.327508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14124","created_at":"2026-07-05T02:36:13.327508+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEIZSLNDOYE7","created_at":"2026-07-05T02:36:13.327508+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEIZSLNDOYE7DSQC","created_at":"2026-07-05T02:36:13.327508+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEIZSLND","created_at":"2026-07-05T02:36:13.327508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01841","citing_title":"Dedicated Inference Engine and Binary-Weight Neural Networks for Lightweight Instance Segmentation","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I","json":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I.json","graph_json":"https://pith.science/api/pith-number/NEIZSLNDOYE7DSQCX5RCR54A5I/graph.json","events_json":"https://pith.science/api/pith-number/NEIZSLNDOYE7DSQCX5RCR54A5I/events.json","paper":"https://pith.science/paper/NEIZSLND"},"agent_actions":{"view_html":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I","download_json":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I.json","view_paper":"https://pith.science/paper/NEIZSLND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.14124&json=true","fetch_graph":"https://pith.science/api/pith-number/NEIZSLNDOYE7DSQCX5RCR54A5I/graph.json","fetch_events":"https://pith.science/api/pith-number/NEIZSLNDOYE7DSQCX5RCR54A5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I/action/storage_attestation","attest_author":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I/action/author_attestation","sign_citation":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I/action/citation_signature","submit_replication":"https://pith.science/pith/NEIZSLNDOYE7DSQCX5RCR54A5I/action/replication_record"}},"created_at":"2026-07-05T02:36:13.327508+00:00","updated_at":"2026-07-05T02:36:13.327508+00:00"}