{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:35J7SQ4JOZFGWGYIQ5CTLS7NAW","short_pith_number":"pith:35J7SQ4J","schema_version":"1.0","canonical_sha256":"df53f94389764a6b1b08874535cbed05810772759eb66755cd2a0da2ea944003","source":{"kind":"arxiv","id":"2306.14525","version":2},"attestation_state":"computed","paper":{"title":"ParameterNet: Parameters Are All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Jianyuan Guo, Kai Han, Yunhe Wang","submitted_at":"2023-06-26T09:01:35Z","abstract_excerpt":"The large-scale visual pretraining has significantly improve the performance of large vision models. However, we observe the \\emph{low FLOPs pitfall} that the existing low-FLOPs models cannot benefit from large-scale pretraining. In this paper, we introduce a novel design principle, termed ParameterNet, aimed at augmenting the number of parameters in large-scale visual pretraining models while minimizing the increase in FLOPs. We leverage dynamic convolutions to incorporate additional parameters into the networks with only a marginal rise in FLOPs. The ParameterNet approach allows low-FLOPs ne"},"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":"2306.14525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-26T09:01:35Z","cross_cats_sorted":[],"title_canon_sha256":"0e291a78d726449290d7d38f245e70267a391a51a1a9bcb7419f69b38227b488","abstract_canon_sha256":"0f7e023f211c9727a47a55da77a80b74da6941512f21e61984cf563712041399"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:17.487771Z","signature_b64":"JN4hDogVSlB2J99+Xkqv9S29+ZIlmBuCEVfE6hkBl4wqPyfzQuEVWIkvqjaEqHHMSnWsPoR/7jW/mslUUkFDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df53f94389764a6b1b08874535cbed05810772759eb66755cd2a0da2ea944003","last_reissued_at":"2026-07-05T07:33:17.487395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:17.487395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParameterNet: Parameters Are All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Jianyuan Guo, Kai Han, Yunhe Wang","submitted_at":"2023-06-26T09:01:35Z","abstract_excerpt":"The large-scale visual pretraining has significantly improve the performance of large vision models. However, we observe the \\emph{low FLOPs pitfall} that the existing low-FLOPs models cannot benefit from large-scale pretraining. In this paper, we introduce a novel design principle, termed ParameterNet, aimed at augmenting the number of parameters in large-scale visual pretraining models while minimizing the increase in FLOPs. We leverage dynamic convolutions to incorporate additional parameters into the networks with only a marginal rise in FLOPs. The ParameterNet approach allows low-FLOPs ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14525","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.14525/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":"2306.14525","created_at":"2026-07-05T07:33:17.487450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14525v2","created_at":"2026-07-05T07:33:17.487450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14525","created_at":"2026-07-05T07:33:17.487450+00:00"},{"alias_kind":"pith_short_12","alias_value":"35J7SQ4JOZFG","created_at":"2026-07-05T07:33:17.487450+00:00"},{"alias_kind":"pith_short_16","alias_value":"35J7SQ4JOZFGWGYI","created_at":"2026-07-05T07:33:17.487450+00:00"},{"alias_kind":"pith_short_8","alias_value":"35J7SQ4J","created_at":"2026-07-05T07:33:17.487450+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/35J7SQ4JOZFGWGYIQ5CTLS7NAW","json":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW.json","graph_json":"https://pith.science/api/pith-number/35J7SQ4JOZFGWGYIQ5CTLS7NAW/graph.json","events_json":"https://pith.science/api/pith-number/35J7SQ4JOZFGWGYIQ5CTLS7NAW/events.json","paper":"https://pith.science/paper/35J7SQ4J"},"agent_actions":{"view_html":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW","download_json":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW.json","view_paper":"https://pith.science/paper/35J7SQ4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14525&json=true","fetch_graph":"https://pith.science/api/pith-number/35J7SQ4JOZFGWGYIQ5CTLS7NAW/graph.json","fetch_events":"https://pith.science/api/pith-number/35J7SQ4JOZFGWGYIQ5CTLS7NAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW/action/storage_attestation","attest_author":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW/action/author_attestation","sign_citation":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW/action/citation_signature","submit_replication":"https://pith.science/pith/35J7SQ4JOZFGWGYIQ5CTLS7NAW/action/replication_record"}},"created_at":"2026-07-05T07:33:17.487450+00:00","updated_at":"2026-07-05T07:33:17.487450+00:00"}