{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BEVJ3FONRDM7AQS7KZH7HYGJZW","short_pith_number":"pith:BEVJ3FON","schema_version":"1.0","canonical_sha256":"092a9d95cd88d9f0425f564ff3e0c9cd9b49a2544dd60df25d55a6d9fae3866e","source":{"kind":"arxiv","id":"1504.01013","version":4},"attestation_state":"computed","paper":{"title":"Efficient piecewise training of deep structured models for semantic segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van dan Hengel, Chunhua Shen, Guosheng Lin, Ian Reid","submitted_at":"2015-04-04T14:26:23Z","abstract_excerpt":"Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information; specifically, we explore `patch-patch' context between image regions, and `patch-background' context. For learning from the patch-patch context, we formulate Conditional Random Fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied to a"},"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":"1504.01013","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-04T14:26:23Z","cross_cats_sorted":[],"title_canon_sha256":"63e201a468318b49cdf1d5f8fc344d810df11087135e0f4787b454bd1504ba64","abstract_canon_sha256":"a027d50790d15bea57b0aabfbb5b71447ab74df3423930a21272521c9cda1bcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:58.580461Z","signature_b64":"4nCTqijVUcJ4+GOiFg3iNsQVtK8FfXIcwwUSdINhp629bZZ4d9eCJ6dus5X4KksvFftV84jJLpHsR2YiZ//qBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"092a9d95cd88d9f0425f564ff3e0c9cd9b49a2544dd60df25d55a6d9fae3866e","last_reissued_at":"2026-05-18T01:12:58.580120Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:58.580120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient piecewise training of deep structured models for semantic segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van dan Hengel, Chunhua Shen, Guosheng Lin, Ian Reid","submitted_at":"2015-04-04T14:26:23Z","abstract_excerpt":"Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information; specifically, we explore `patch-patch' context between image regions, and `patch-background' context. For learning from the patch-patch context, we formulate Conditional Random Fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.01013","kind":"arxiv","version":4},"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":"1504.01013","created_at":"2026-05-18T01:12:58.580175+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.01013v4","created_at":"2026-05-18T01:12:58.580175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.01013","created_at":"2026-05-18T01:12:58.580175+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEVJ3FONRDM7","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEVJ3FONRDM7AQS7","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEVJ3FON","created_at":"2026-05-18T12:29:14.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW","json":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW.json","graph_json":"https://pith.science/api/pith-number/BEVJ3FONRDM7AQS7KZH7HYGJZW/graph.json","events_json":"https://pith.science/api/pith-number/BEVJ3FONRDM7AQS7KZH7HYGJZW/events.json","paper":"https://pith.science/paper/BEVJ3FON"},"agent_actions":{"view_html":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW","download_json":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW.json","view_paper":"https://pith.science/paper/BEVJ3FON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.01013&json=true","fetch_graph":"https://pith.science/api/pith-number/BEVJ3FONRDM7AQS7KZH7HYGJZW/graph.json","fetch_events":"https://pith.science/api/pith-number/BEVJ3FONRDM7AQS7KZH7HYGJZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW/action/storage_attestation","attest_author":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW/action/author_attestation","sign_citation":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW/action/citation_signature","submit_replication":"https://pith.science/pith/BEVJ3FONRDM7AQS7KZH7HYGJZW/action/replication_record"}},"created_at":"2026-05-18T01:12:58.580175+00:00","updated_at":"2026-05-18T01:12:58.580175+00:00"}