{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CDT5DPD4ICMMG6LUKSI7WGZMSM","short_pith_number":"pith:CDT5DPD4","schema_version":"1.0","canonical_sha256":"10e7d1bc7c4098c379745491fb1b2c932430968a1ec5683fa10c3b3a9b330be4","source":{"kind":"arxiv","id":"1605.02264","version":2},"attestation_state":"computed","paper":{"title":"Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless C. Fowlkes, Golnaz Ghiasi","submitted_at":"2016-05-08T02:25:12Z","abstract_excerpt":"CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling. This paper makes two contributions: (1) We demonstrate that while the apparent spatial resolution of convolutional feature maps is low, the high-dimensional feature representation contains significant sub-pixel localization information. (2) We describe a multi-resolution reconstruction architecture based on a Laplacian pyramid that uses skip connections from higher resolution feature maps and multiplicative gating to su"},"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":"1605.02264","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-08T02:25:12Z","cross_cats_sorted":[],"title_canon_sha256":"05e26f3b0fc0d4a37cf8c5db4d8f16add29f6db301b79a77205022e4dc5e8e19","abstract_canon_sha256":"f4cb95962157daa94b60e52832979b6a892d9cc8d6952929780847c98050fda6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:14.412197Z","signature_b64":"k2vaMnAoYRk+UYMsD+FSy4gSl8Cx6vJOVH8PEhJrf6pJcB2rVUwW58HQe2pkrqpZ6S8rI8M++VUjy0LVH9tVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10e7d1bc7c4098c379745491fb1b2c932430968a1ec5683fa10c3b3a9b330be4","last_reissued_at":"2026-05-18T01:10:14.411775Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:14.411775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless C. Fowlkes, Golnaz Ghiasi","submitted_at":"2016-05-08T02:25:12Z","abstract_excerpt":"CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling. This paper makes two contributions: (1) We demonstrate that while the apparent spatial resolution of convolutional feature maps is low, the high-dimensional feature representation contains significant sub-pixel localization information. (2) We describe a multi-resolution reconstruction architecture based on a Laplacian pyramid that uses skip connections from higher resolution feature maps and multiplicative gating to su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.02264","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":"1605.02264","created_at":"2026-05-18T01:10:14.411834+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.02264v2","created_at":"2026-05-18T01:10:14.411834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.02264","created_at":"2026-05-18T01:10:14.411834+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDT5DPD4ICMM","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDT5DPD4ICMMG6LU","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDT5DPD4","created_at":"2026-05-18T12:30:09.641336+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":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM","json":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM.json","graph_json":"https://pith.science/api/pith-number/CDT5DPD4ICMMG6LUKSI7WGZMSM/graph.json","events_json":"https://pith.science/api/pith-number/CDT5DPD4ICMMG6LUKSI7WGZMSM/events.json","paper":"https://pith.science/paper/CDT5DPD4"},"agent_actions":{"view_html":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM","download_json":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM.json","view_paper":"https://pith.science/paper/CDT5DPD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.02264&json=true","fetch_graph":"https://pith.science/api/pith-number/CDT5DPD4ICMMG6LUKSI7WGZMSM/graph.json","fetch_events":"https://pith.science/api/pith-number/CDT5DPD4ICMMG6LUKSI7WGZMSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM/action/storage_attestation","attest_author":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM/action/author_attestation","sign_citation":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM/action/citation_signature","submit_replication":"https://pith.science/pith/CDT5DPD4ICMMG6LUKSI7WGZMSM/action/replication_record"}},"created_at":"2026-05-18T01:10:14.411834+00:00","updated_at":"2026-05-18T01:10:14.411834+00:00"}