{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SDPGLFVD36AJ62PS6M43237L7B","short_pith_number":"pith:SDPGLFVD","schema_version":"1.0","canonical_sha256":"90de6596a3df809f69f2f339bd6febf85565b5f6d9a209eee0f423e6f51dea1e","source":{"kind":"arxiv","id":"2101.10156","version":1},"attestation_state":"computed","paper":{"title":"Mask-based Data Augmentation for Semi-supervised Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gady Agam, Kaiyue Zhu, Xu Ouyang, Ying Chen","submitted_at":"2021-01-25T15:09:34Z","abstract_excerpt":"Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive. Semi-supervised learning algorithms address this issue by utilizing unlabeled data and so reduce the amount of labeled data needed for training. In particular, data augmentation techniques such as CutMix and ClassMix generate additional training data from existing labeled data. In this paper we propose a new approach for data"},"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":"2101.10156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-25T15:09:34Z","cross_cats_sorted":[],"title_canon_sha256":"2d7f058dfe84c5f778fa1f2ab1351ed7ba5d198bd73983ee3712653600e12811","abstract_canon_sha256":"8524e60d6341cf937fcada13c301bb6526d89f08d19aa389be2281fe7f371269"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:26.359378Z","signature_b64":"yTpN2V+od1cccBHxzP9BzoBnNrElN3+rShW1qa+NEeLNSx39hg+gu0HKebjseCX1wm3I0zd7ZjmiZaJ2bWhcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90de6596a3df809f69f2f339bd6febf85565b5f6d9a209eee0f423e6f51dea1e","last_reissued_at":"2026-07-05T02:09:26.358904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:26.358904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mask-based Data Augmentation for Semi-supervised Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gady Agam, Kaiyue Zhu, Xu Ouyang, Ying Chen","submitted_at":"2021-01-25T15:09:34Z","abstract_excerpt":"Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive. Semi-supervised learning algorithms address this issue by utilizing unlabeled data and so reduce the amount of labeled data needed for training. In particular, data augmentation techniques such as CutMix and ClassMix generate additional training data from existing labeled data. In this paper we propose a new approach for data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10156","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/2101.10156/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":"2101.10156","created_at":"2026-07-05T02:09:26.358964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.10156v1","created_at":"2026-07-05T02:09:26.358964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10156","created_at":"2026-07-05T02:09:26.358964+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDPGLFVD36AJ","created_at":"2026-07-05T02:09:26.358964+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDPGLFVD36AJ62PS","created_at":"2026-07-05T02:09:26.358964+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDPGLFVD","created_at":"2026-07-05T02:09:26.358964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07691","citing_title":"Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B","json":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B.json","graph_json":"https://pith.science/api/pith-number/SDPGLFVD36AJ62PS6M43237L7B/graph.json","events_json":"https://pith.science/api/pith-number/SDPGLFVD36AJ62PS6M43237L7B/events.json","paper":"https://pith.science/paper/SDPGLFVD"},"agent_actions":{"view_html":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B","download_json":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B.json","view_paper":"https://pith.science/paper/SDPGLFVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.10156&json=true","fetch_graph":"https://pith.science/api/pith-number/SDPGLFVD36AJ62PS6M43237L7B/graph.json","fetch_events":"https://pith.science/api/pith-number/SDPGLFVD36AJ62PS6M43237L7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B/action/storage_attestation","attest_author":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B/action/author_attestation","sign_citation":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B/action/citation_signature","submit_replication":"https://pith.science/pith/SDPGLFVD36AJ62PS6M43237L7B/action/replication_record"}},"created_at":"2026-07-05T02:09:26.358964+00:00","updated_at":"2026-07-05T02:09:26.358964+00:00"}