{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NVLHYM3VUO6DIUNWF3LOW64W47","short_pith_number":"pith:NVLHYM3V","schema_version":"1.0","canonical_sha256":"6d567c3375a3bc3451b62ed6eb7b96e7d64403fdb33a4019a45742de95427430","source":{"kind":"arxiv","id":"2005.02551","version":1},"attestation_state":"computed","paper":{"title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang (HKUST), Ho Kei Cheng (HKUST), Jihoon Chung (HKUST), Yu-Wing Tai (Tencent)","submitted_at":"2020-05-06T01:38:03Z","abstract_excerpt":"State-of-the-art semantic segmentation methods were almost exclusively trained on images within a fixed resolution range. These segmentations are inaccurate for very high-resolution images since using bicubic upsampling of low-resolution segmentation does not adequately capture high-resolution details along object boundaries. In this paper, we propose a novel approach to address the high-resolution segmentation problem without using any high-resolution training data. The key insight is our CascadePSP network which refines and corrects local boundaries whenever possible. Although our network is"},"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":"2005.02551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-06T01:38:03Z","cross_cats_sorted":[],"title_canon_sha256":"ca81b6959294ec2939b7fdf3b13a2d2e2ea18d9cdc436f729322093102d348bd","abstract_canon_sha256":"feed844b30c3ca2c220f0167d4dbd62714d69c8ea9063957432cbf6934ad88a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:53.532641Z","signature_b64":"r6n8Spy6Y7ey0IuUxSePmj3pT/6fSusYTJfU6B6qmWwLuVoR5vT4BSTaCWRGkrieOdJlcW+0PmMESzvfNeobCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d567c3375a3bc3451b62ed6eb7b96e7d64403fdb33a4019a45742de95427430","last_reissued_at":"2026-07-05T01:00:53.532186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:53.532186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang (HKUST), Ho Kei Cheng (HKUST), Jihoon Chung (HKUST), Yu-Wing Tai (Tencent)","submitted_at":"2020-05-06T01:38:03Z","abstract_excerpt":"State-of-the-art semantic segmentation methods were almost exclusively trained on images within a fixed resolution range. These segmentations are inaccurate for very high-resolution images since using bicubic upsampling of low-resolution segmentation does not adequately capture high-resolution details along object boundaries. In this paper, we propose a novel approach to address the high-resolution segmentation problem without using any high-resolution training data. The key insight is our CascadePSP network which refines and corrects local boundaries whenever possible. Although our network is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02551","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/2005.02551/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":"2005.02551","created_at":"2026-07-05T01:00:53.532243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.02551v1","created_at":"2026-07-05T01:00:53.532243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02551","created_at":"2026-07-05T01:00:53.532243+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVLHYM3VUO6D","created_at":"2026-07-05T01:00:53.532243+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVLHYM3VUO6DIUNW","created_at":"2026-07-05T01:00:53.532243+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVLHYM3V","created_at":"2026-07-05T01:00:53.532243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06839","citing_title":"ToonOut: Fine-tuned Background-Removal for Anime Characters","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47","json":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47.json","graph_json":"https://pith.science/api/pith-number/NVLHYM3VUO6DIUNWF3LOW64W47/graph.json","events_json":"https://pith.science/api/pith-number/NVLHYM3VUO6DIUNWF3LOW64W47/events.json","paper":"https://pith.science/paper/NVLHYM3V"},"agent_actions":{"view_html":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47","download_json":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47.json","view_paper":"https://pith.science/paper/NVLHYM3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.02551&json=true","fetch_graph":"https://pith.science/api/pith-number/NVLHYM3VUO6DIUNWF3LOW64W47/graph.json","fetch_events":"https://pith.science/api/pith-number/NVLHYM3VUO6DIUNWF3LOW64W47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47/action/storage_attestation","attest_author":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47/action/author_attestation","sign_citation":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47/action/citation_signature","submit_replication":"https://pith.science/pith/NVLHYM3VUO6DIUNWF3LOW64W47/action/replication_record"}},"created_at":"2026-07-05T01:00:53.532243+00:00","updated_at":"2026-07-05T01:00:53.532243+00:00"}