{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:52WEK4QXOOFS5N55KY7G6GIEL3","short_pith_number":"pith:52WEK4QX","schema_version":"1.0","canonical_sha256":"eeac457217738b2eb7bd563e6f19045ef595e1e4693e78235f9d15852ede0d3f","source":{"kind":"arxiv","id":"1511.07386","version":2},"attestation_state":"computed","paper":{"title":"Pushing the Boundaries of Boundary Detection using Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Iasonas Kokkinos","submitted_at":"2015-11-23T19:54:09Z","abstract_excerpt":"In this work we show that adapting Deep Convolutional Neural Network training to the task of boundary detection can result in substantial improvements over the current state-of-the-art in boundary detection.\n  Our contributions consist firstly in combining a careful design of the loss for boundary detection training, a multi-resolution architecture and training with external data to improve the detection accuracy of the current state of the art. When measured on the standard Berkeley Segmentation Dataset, we improve theoptimal dataset scale F-measure from 0.780 to 0.808 - while human performan"},"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":"1511.07386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-23T19:54:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bce38c30915dbd47030a50e888897532e679d627ad897f54d63541daeddd1422","abstract_canon_sha256":"3ad7602ae2ef63d6173aacc62ec4f69b40f49b9d8b9974ac436215fd2e4f246d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:10.053514Z","signature_b64":"RglDmMn1U9wq95Deijb8zXdn4bt9Vn6qwmokepswpNXrei7orWi5ujSqxT4RgWPsW/l2WvIzs88+I5WGwsRlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeac457217738b2eb7bd563e6f19045ef595e1e4693e78235f9d15852ede0d3f","last_reissued_at":"2026-05-18T01:22:10.053017Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:10.053017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pushing the Boundaries of Boundary Detection using Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Iasonas Kokkinos","submitted_at":"2015-11-23T19:54:09Z","abstract_excerpt":"In this work we show that adapting Deep Convolutional Neural Network training to the task of boundary detection can result in substantial improvements over the current state-of-the-art in boundary detection.\n  Our contributions consist firstly in combining a careful design of the loss for boundary detection training, a multi-resolution architecture and training with external data to improve the detection accuracy of the current state of the art. When measured on the standard Berkeley Segmentation Dataset, we improve theoptimal dataset scale F-measure from 0.780 to 0.808 - while human performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07386","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":""},"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":"1511.07386","created_at":"2026-05-18T01:22:10.053089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07386v2","created_at":"2026-05-18T01:22:10.053089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07386","created_at":"2026-05-18T01:22:10.053089+00:00"},{"alias_kind":"pith_short_12","alias_value":"52WEK4QXOOFS","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"52WEK4QXOOFS5N55","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"52WEK4QX","created_at":"2026-05-18T12:29:05.191682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.10303","citing_title":"Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3","json":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3.json","graph_json":"https://pith.science/api/pith-number/52WEK4QXOOFS5N55KY7G6GIEL3/graph.json","events_json":"https://pith.science/api/pith-number/52WEK4QXOOFS5N55KY7G6GIEL3/events.json","paper":"https://pith.science/paper/52WEK4QX"},"agent_actions":{"view_html":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3","download_json":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3.json","view_paper":"https://pith.science/paper/52WEK4QX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07386&json=true","fetch_graph":"https://pith.science/api/pith-number/52WEK4QXOOFS5N55KY7G6GIEL3/graph.json","fetch_events":"https://pith.science/api/pith-number/52WEK4QXOOFS5N55KY7G6GIEL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3/action/storage_attestation","attest_author":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3/action/author_attestation","sign_citation":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3/action/citation_signature","submit_replication":"https://pith.science/pith/52WEK4QXOOFS5N55KY7G6GIEL3/action/replication_record"}},"created_at":"2026-05-18T01:22:10.053089+00:00","updated_at":"2026-05-18T01:22:10.053089+00:00"}