{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:M6X3LOPRRME4YWBY7OV6FAPOLC","short_pith_number":"pith:M6X3LOPR","schema_version":"1.0","canonical_sha256":"67afb5b9f18b09cc5838fbabe281ee5895d7744fe5ea5233a7cd9dd8783e6cda","source":{"kind":"arxiv","id":"2005.13363","version":2},"attestation_state":"computed","paper":{"title":"GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibin Ling, Weisi Lin, Yangyan Li, Ying Chen, Yongtao Wang, Zhi Tang, Zhuoying Wang","submitted_at":"2020-05-27T13:46:58Z","abstract_excerpt":"Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation. State-of-the-art pixel labeling neural networks widely exploit conventional scale-transfer operations, i.e., up-sampling and down-sampling to learn multi-scale features. In this work, we find that these operations lead to scale-confused features and suboptimal performance because they are spatial-invariant and directly transit all feature information cross scales without spatial selection. To address this issue, we propose the Gat"},"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":"2005.13363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-27T13:46:58Z","cross_cats_sorted":[],"title_canon_sha256":"5ca27041816c774fa742a429736357c925d2d72bbf943b717e48471aa56929f3","abstract_canon_sha256":"e902f1ea954126566969b826e9044876d1105bd8b99fb0f926c3074210641e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:00.474054Z","signature_b64":"VvV9OvLLG0vot3Rn5ADIN9T+iB/yvP/cB5E5XZW0sacTZ1r/ZXEf5Jy/BOjhDkSlIzN9wEs6oXzaLXectDj9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67afb5b9f18b09cc5838fbabe281ee5895d7744fe5ea5233a7cd9dd8783e6cda","last_reissued_at":"2026-07-05T01:14:00.473687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:00.473687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibin Ling, Weisi Lin, Yangyan Li, Ying Chen, Yongtao Wang, Zhi Tang, Zhuoying Wang","submitted_at":"2020-05-27T13:46:58Z","abstract_excerpt":"Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation. State-of-the-art pixel labeling neural networks widely exploit conventional scale-transfer operations, i.e., up-sampling and down-sampling to learn multi-scale features. In this work, we find that these operations lead to scale-confused features and suboptimal performance because they are spatial-invariant and directly transit all feature information cross scales without spatial selection. To address this issue, we propose the Gat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13363","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/2005.13363/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":"2005.13363","created_at":"2026-07-05T01:14:00.473741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.13363v2","created_at":"2026-07-05T01:14:00.473741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13363","created_at":"2026-07-05T01:14:00.473741+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6X3LOPRRME4","created_at":"2026-07-05T01:14:00.473741+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6X3LOPRRME4YWBY","created_at":"2026-07-05T01:14:00.473741+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6X3LOPR","created_at":"2026-07-05T01:14:00.473741+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/M6X3LOPRRME4YWBY7OV6FAPOLC","json":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC.json","graph_json":"https://pith.science/api/pith-number/M6X3LOPRRME4YWBY7OV6FAPOLC/graph.json","events_json":"https://pith.science/api/pith-number/M6X3LOPRRME4YWBY7OV6FAPOLC/events.json","paper":"https://pith.science/paper/M6X3LOPR"},"agent_actions":{"view_html":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC","download_json":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC.json","view_paper":"https://pith.science/paper/M6X3LOPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.13363&json=true","fetch_graph":"https://pith.science/api/pith-number/M6X3LOPRRME4YWBY7OV6FAPOLC/graph.json","fetch_events":"https://pith.science/api/pith-number/M6X3LOPRRME4YWBY7OV6FAPOLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC/action/storage_attestation","attest_author":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC/action/author_attestation","sign_citation":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC/action/citation_signature","submit_replication":"https://pith.science/pith/M6X3LOPRRME4YWBY7OV6FAPOLC/action/replication_record"}},"created_at":"2026-07-05T01:14:00.473741+00:00","updated_at":"2026-07-05T01:14:00.473741+00:00"}