{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PADC7PSZW5Y7MJZZU6PIUEEXFE","short_pith_number":"pith:PADC7PSZ","schema_version":"1.0","canonical_sha256":"78062fbe59b771f62739a79e8a10972919d5a85eed82164be888926e8831bfd0","source":{"kind":"arxiv","id":"1903.03793","version":1},"attestation_state":"computed","paper":{"title":"SSN: Learning Sparse Switchable Normalization via SparsestMax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyu Li, Ping Luo, Ruimao Zhang, Tianjian Meng, Wenqi Shao, Xiaogang Wang, Yudian Li","submitted_at":"2019-03-09T12:48:52Z","abstract_excerpt":"Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different normalizers for different convolution layers of a ConvNet. However, SN uses softmax function to learn importance ratios to combine normalizers, leading to redundant computations compared to a single normalizer.\n  This work addresses this issue by presenting Sparse Switchable Normalization (SSN) where the importance ratios are constrained to be sparse. Unlike $"},"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":"1903.03793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-09T12:48:52Z","cross_cats_sorted":[],"title_canon_sha256":"9dca9ce0822c193603f458a66d6a96bd34a70a0423e69fbb4322a4fba2f06580","abstract_canon_sha256":"55bfc27e09180e3aa266a1b37093aa71da3db64c3bcad12485bbc56e29d5b910"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:40.941495Z","signature_b64":"OW9viMpFvEYTcjlgrNnZEuwyDUMhJG/+XBsyLFOYENDPxAmcTEDs3EWCnhLuzInwMgV0dyVj0NNJLOgCn1p9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78062fbe59b771f62739a79e8a10972919d5a85eed82164be888926e8831bfd0","last_reissued_at":"2026-05-17T23:51:40.941031Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:40.941031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSN: Learning Sparse Switchable Normalization via SparsestMax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyu Li, Ping Luo, Ruimao Zhang, Tianjian Meng, Wenqi Shao, Xiaogang Wang, Yudian Li","submitted_at":"2019-03-09T12:48:52Z","abstract_excerpt":"Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different normalizers for different convolution layers of a ConvNet. However, SN uses softmax function to learn importance ratios to combine normalizers, leading to redundant computations compared to a single normalizer.\n  This work addresses this issue by presenting Sparse Switchable Normalization (SSN) where the importance ratios are constrained to be sparse. Unlike $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03793","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":"1903.03793","created_at":"2026-05-17T23:51:40.941101+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03793v1","created_at":"2026-05-17T23:51:40.941101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03793","created_at":"2026-05-17T23:51:40.941101+00:00"},{"alias_kind":"pith_short_12","alias_value":"PADC7PSZW5Y7","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PADC7PSZW5Y7MJZZ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PADC7PSZ","created_at":"2026-05-18T12:33:24.271573+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/PADC7PSZW5Y7MJZZU6PIUEEXFE","json":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE.json","graph_json":"https://pith.science/api/pith-number/PADC7PSZW5Y7MJZZU6PIUEEXFE/graph.json","events_json":"https://pith.science/api/pith-number/PADC7PSZW5Y7MJZZU6PIUEEXFE/events.json","paper":"https://pith.science/paper/PADC7PSZ"},"agent_actions":{"view_html":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE","download_json":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE.json","view_paper":"https://pith.science/paper/PADC7PSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03793&json=true","fetch_graph":"https://pith.science/api/pith-number/PADC7PSZW5Y7MJZZU6PIUEEXFE/graph.json","fetch_events":"https://pith.science/api/pith-number/PADC7PSZW5Y7MJZZU6PIUEEXFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE/action/storage_attestation","attest_author":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE/action/author_attestation","sign_citation":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE/action/citation_signature","submit_replication":"https://pith.science/pith/PADC7PSZW5Y7MJZZU6PIUEEXFE/action/replication_record"}},"created_at":"2026-05-17T23:51:40.941101+00:00","updated_at":"2026-05-17T23:51:40.941101+00:00"}