{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JVDKL4O7W4III6LG4U6TKTHH5V","short_pith_number":"pith:JVDKL4O7","schema_version":"1.0","canonical_sha256":"4d46a5f1dfb710847966e53d354ce7ed4269d5be73508cb14f58fcfb10aad398","source":{"kind":"arxiv","id":"1907.11840","version":1},"attestation_state":"computed","paper":{"title":"Learning Instance-wise Sparsity for Accelerating Deep Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chuanjian Liu, Chunjing Xu, Kai Han, Yunhe Wang","submitted_at":"2019-07-27T02:59:38Z","abstract_excerpt":"Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or filters without data, e.g., pruning and decomposition. In contrast, we study this problem from a different perspective by respecting the difference between data. An instance-wise feature pruning is developed by identifying informative features for different instances. Specifically, by investigating a feature decay regularization, we expect intermediate feature"},"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":"1907.11840","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-27T02:59:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1325fcfc37a0ba781bdabc2d339a4b3ff590c2118429e60a589cca188a79508a","abstract_canon_sha256":"6509c3f4fb248dd18272ea396e94d1067d22910f1810de1ca94130c8f7f264b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:22.881253Z","signature_b64":"3dek6eQRrwn9geo89gHB6JJcb0+EOJXxkGxw962rr4yw9wIV6+KP322wfU+C9NNFM816wconvyHMHfviFV1rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d46a5f1dfb710847966e53d354ce7ed4269d5be73508cb14f58fcfb10aad398","last_reissued_at":"2026-05-17T23:39:22.880703Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:22.880703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Instance-wise Sparsity for Accelerating Deep Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chuanjian Liu, Chunjing Xu, Kai Han, Yunhe Wang","submitted_at":"2019-07-27T02:59:38Z","abstract_excerpt":"Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or filters without data, e.g., pruning and decomposition. In contrast, we study this problem from a different perspective by respecting the difference between data. An instance-wise feature pruning is developed by identifying informative features for different instances. Specifically, by investigating a feature decay regularization, we expect intermediate feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11840","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":"1907.11840","created_at":"2026-05-17T23:39:22.880797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.11840v1","created_at":"2026-05-17T23:39:22.880797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11840","created_at":"2026-05-17T23:39:22.880797+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVDKL4O7W4II","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVDKL4O7W4III6LG","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVDKL4O7","created_at":"2026-05-18T12:33:21.387695+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/JVDKL4O7W4III6LG4U6TKTHH5V","json":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V.json","graph_json":"https://pith.science/api/pith-number/JVDKL4O7W4III6LG4U6TKTHH5V/graph.json","events_json":"https://pith.science/api/pith-number/JVDKL4O7W4III6LG4U6TKTHH5V/events.json","paper":"https://pith.science/paper/JVDKL4O7"},"agent_actions":{"view_html":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V","download_json":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V.json","view_paper":"https://pith.science/paper/JVDKL4O7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.11840&json=true","fetch_graph":"https://pith.science/api/pith-number/JVDKL4O7W4III6LG4U6TKTHH5V/graph.json","fetch_events":"https://pith.science/api/pith-number/JVDKL4O7W4III6LG4U6TKTHH5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V/action/storage_attestation","attest_author":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V/action/author_attestation","sign_citation":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V/action/citation_signature","submit_replication":"https://pith.science/pith/JVDKL4O7W4III6LG4U6TKTHH5V/action/replication_record"}},"created_at":"2026-05-17T23:39:22.880797+00:00","updated_at":"2026-05-17T23:39:22.880797+00:00"}