{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OMOAGSAV6ANDDHRT22I6BOGMS7","short_pith_number":"pith:OMOAGSAV","schema_version":"1.0","canonical_sha256":"731c034815f01a319e33d691e0b8cc97f8a4d02396f9c2a441fae11510a66c10","source":{"kind":"arxiv","id":"2103.01795","version":2},"attestation_state":"computed","paper":{"title":"Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guosheng Lin, Qingyao Wu, Ruizhou Sun, Yukun Su","submitted_at":"2021-03-02T15:05:09Z","abstract_excerpt":"Data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challenging problem that has been deeply studied in recent years, conventional data augmentation approaches for WSSS usually employ geometrical transformations, random cropping and color jittering. However, merely increasing the same contextual semantic data does not bring much gain to the networks to distinguish the objects, e.g., the correct image-level classification of \"aeroplane"},"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":"2103.01795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-02T15:05:09Z","cross_cats_sorted":[],"title_canon_sha256":"9bb85b887f7736d5df0a6813de0ce87f21508a6d1f2e645e3494ce34fb386fc8","abstract_canon_sha256":"3de7ac180c287191d004ca986e68dec6927c1a8740a3c6293b24c573aa5f41f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:39.470644Z","signature_b64":"hoiwGFcu0+mffeoJIaxvIUrNF4BsYFuObniCD7fH2N0Hyd7XnKi6WPTowLxNKZ/KcDtsgQYWRync10N7aTb3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"731c034815f01a319e33d691e0b8cc97f8a4d02396f9c2a441fae11510a66c10","last_reissued_at":"2026-07-05T03:26:39.470093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:39.470093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guosheng Lin, Qingyao Wu, Ruizhou Sun, Yukun Su","submitted_at":"2021-03-02T15:05:09Z","abstract_excerpt":"Data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challenging problem that has been deeply studied in recent years, conventional data augmentation approaches for WSSS usually employ geometrical transformations, random cropping and color jittering. However, merely increasing the same contextual semantic data does not bring much gain to the networks to distinguish the objects, e.g., the correct image-level classification of \"aeroplane"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01795","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/2103.01795/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":"2103.01795","created_at":"2026-07-05T03:26:39.470169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.01795v2","created_at":"2026-07-05T03:26:39.470169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01795","created_at":"2026-07-05T03:26:39.470169+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMOAGSAV6AND","created_at":"2026-07-05T03:26:39.470169+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMOAGSAV6ANDDHRT","created_at":"2026-07-05T03:26:39.470169+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMOAGSAV","created_at":"2026-07-05T03:26:39.470169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21959","citing_title":"Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularization","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7","json":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7.json","graph_json":"https://pith.science/api/pith-number/OMOAGSAV6ANDDHRT22I6BOGMS7/graph.json","events_json":"https://pith.science/api/pith-number/OMOAGSAV6ANDDHRT22I6BOGMS7/events.json","paper":"https://pith.science/paper/OMOAGSAV"},"agent_actions":{"view_html":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7","download_json":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7.json","view_paper":"https://pith.science/paper/OMOAGSAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.01795&json=true","fetch_graph":"https://pith.science/api/pith-number/OMOAGSAV6ANDDHRT22I6BOGMS7/graph.json","fetch_events":"https://pith.science/api/pith-number/OMOAGSAV6ANDDHRT22I6BOGMS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7/action/storage_attestation","attest_author":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7/action/author_attestation","sign_citation":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7/action/citation_signature","submit_replication":"https://pith.science/pith/OMOAGSAV6ANDDHRT22I6BOGMS7/action/replication_record"}},"created_at":"2026-07-05T03:26:39.470169+00:00","updated_at":"2026-07-05T03:26:39.470169+00:00"}