{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z4GJS42EUE6WLUPYVCRNCLXVMS","short_pith_number":"pith:Z4GJS42E","schema_version":"1.0","canonical_sha256":"cf0c997344a13d65d1f8a8a2d12ef5649299964c8b515397651e1422de83ad3d","source":{"kind":"arxiv","id":"2012.10782","version":2},"attestation_state":"computed","paper":{"title":"Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian K\\\"oring, Dengxin Dai, Luc Van Gool, Lukas Hoyer, Suman Saha, Yuhua Chen","submitted_at":"2020-12-19T21:18:03Z","abstract_excerpt":"Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. In particular, we propose three key contributions: (1) We transfer knowledge from features learned during self-supervised depth estimation to semantic segmentation, (2) we implement a strong data augment"},"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":"2012.10782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-19T21:18:03Z","cross_cats_sorted":[],"title_canon_sha256":"79c8aee70ee94149058ee7f2ffb0fa28617d66356a1857ec5325feb4be4f732d","abstract_canon_sha256":"b3a74d4feaede2fa0efa28ae27f06713403e969a3e1c6f66d53376b25b942c1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:54.512256Z","signature_b64":"mJP1OfvSeH18r7HvHKSDDUtPChEqHhhnK2cnXoWxtotHx86BR1mSOkxL1l1aaPXRthqEjK4zoBbtzKe5WlGJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf0c997344a13d65d1f8a8a2d12ef5649299964c8b515397651e1422de83ad3d","last_reissued_at":"2026-07-05T02:28:54.511766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:54.511766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian K\\\"oring, Dengxin Dai, Luc Van Gool, Lukas Hoyer, Suman Saha, Yuhua Chen","submitted_at":"2020-12-19T21:18:03Z","abstract_excerpt":"Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. In particular, we propose three key contributions: (1) We transfer knowledge from features learned during self-supervised depth estimation to semantic segmentation, (2) we implement a strong data augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10782","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/2012.10782/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":"2012.10782","created_at":"2026-07-05T02:28:54.511824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.10782v2","created_at":"2026-07-05T02:28:54.511824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10782","created_at":"2026-07-05T02:28:54.511824+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4GJS42EUE6W","created_at":"2026-07-05T02:28:54.511824+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4GJS42EUE6WLUPY","created_at":"2026-07-05T02:28:54.511824+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4GJS42E","created_at":"2026-07-05T02:28:54.511824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29599","citing_title":"How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS","json":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS.json","graph_json":"https://pith.science/api/pith-number/Z4GJS42EUE6WLUPYVCRNCLXVMS/graph.json","events_json":"https://pith.science/api/pith-number/Z4GJS42EUE6WLUPYVCRNCLXVMS/events.json","paper":"https://pith.science/paper/Z4GJS42E"},"agent_actions":{"view_html":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS","download_json":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS.json","view_paper":"https://pith.science/paper/Z4GJS42E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.10782&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4GJS42EUE6WLUPYVCRNCLXVMS/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4GJS42EUE6WLUPYVCRNCLXVMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS/action/storage_attestation","attest_author":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS/action/author_attestation","sign_citation":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS/action/citation_signature","submit_replication":"https://pith.science/pith/Z4GJS42EUE6WLUPYVCRNCLXVMS/action/replication_record"}},"created_at":"2026-07-05T02:28:54.511824+00:00","updated_at":"2026-07-05T02:28:54.511824+00:00"}