{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2VV6VA7E2XVN6VWT7J6OGJ45MN","short_pith_number":"pith:2VV6VA7E","schema_version":"1.0","canonical_sha256":"d56bea83e4d5eadf56d3fa7ce3279d635a88d1a58541dcdffbd8c4c42d9c15ae","source":{"kind":"arxiv","id":"2106.08601","version":5},"attestation_state":"computed","paper":{"title":"Self-Supervised GANs with Label Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Huawei Shen, Liang Hou, Qi Cao, Xueqi Cheng","submitted_at":"2021-06-16T07:58:00Z","abstract_excerpt":"Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment. However, the separate self-supervised tasks in existing self-supervised GANs cause a goal inconsistent with generative modeling due to the fact that their self-supervised classifiers are agnostic to the generator distribution. To address this problem, we propose a novel self-supervised GAN that unifies the GAN task with the self-supervised task by augmenting the GAN labels (r"},"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":"2106.08601","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T07:58:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7362ebd99640a4770dd3c26e18e54b407c55c6b9a528a5a91a9d2a0ad1266123","abstract_canon_sha256":"669d1a9d7fc181a4a15bee1740826457dd0f218c5f92a9f0e2cc74013600e85f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:42.037058Z","signature_b64":"csa7hB+VDdtHuUQEgGh8jHRZ/xnRQYJ9tswhmMfDfA7jn2LTyQ/vEGYy6msYgU1ZIitLGjWKFjAmGSKN4nW+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d56bea83e4d5eadf56d3fa7ce3279d635a88d1a58541dcdffbd8c4c42d9c15ae","last_reissued_at":"2026-07-05T03:48:42.036535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:42.036535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised GANs with Label Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Huawei Shen, Liang Hou, Qi Cao, Xueqi Cheng","submitted_at":"2021-06-16T07:58:00Z","abstract_excerpt":"Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment. However, the separate self-supervised tasks in existing self-supervised GANs cause a goal inconsistent with generative modeling due to the fact that their self-supervised classifiers are agnostic to the generator distribution. To address this problem, we propose a novel self-supervised GAN that unifies the GAN task with the self-supervised task by augmenting the GAN labels (r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08601","kind":"arxiv","version":5},"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/2106.08601/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":"2106.08601","created_at":"2026-07-05T03:48:42.036604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.08601v5","created_at":"2026-07-05T03:48:42.036604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08601","created_at":"2026-07-05T03:48:42.036604+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VV6VA7E2XVN","created_at":"2026-07-05T03:48:42.036604+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VV6VA7E2XVN6VWT","created_at":"2026-07-05T03:48:42.036604+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VV6VA7E","created_at":"2026-07-05T03:48:42.036604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN","json":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN.json","graph_json":"https://pith.science/api/pith-number/2VV6VA7E2XVN6VWT7J6OGJ45MN/graph.json","events_json":"https://pith.science/api/pith-number/2VV6VA7E2XVN6VWT7J6OGJ45MN/events.json","paper":"https://pith.science/paper/2VV6VA7E"},"agent_actions":{"view_html":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN","download_json":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN.json","view_paper":"https://pith.science/paper/2VV6VA7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.08601&json=true","fetch_graph":"https://pith.science/api/pith-number/2VV6VA7E2XVN6VWT7J6OGJ45MN/graph.json","fetch_events":"https://pith.science/api/pith-number/2VV6VA7E2XVN6VWT7J6OGJ45MN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN/action/storage_attestation","attest_author":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN/action/author_attestation","sign_citation":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN/action/citation_signature","submit_replication":"https://pith.science/pith/2VV6VA7E2XVN6VWT7J6OGJ45MN/action/replication_record"}},"created_at":"2026-07-05T03:48:42.036604+00:00","updated_at":"2026-07-05T03:48:42.036604+00:00"}