{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YNQPJFVCZD62YJ7PGAV4K4W5JX","short_pith_number":"pith:YNQPJFVC","schema_version":"1.0","canonical_sha256":"c360f496a2c8fdac27ef302bc572dd4dd645ae0d0dc96684b9a2c5d93d8a54cc","source":{"kind":"arxiv","id":"2112.02450","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Feature Interpolation for Low-Shot Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibin Hang, Mengyu Dai, Xiaoyang Guo","submitted_at":"2021-12-04T23:55:46Z","abstract_excerpt":"Training of generative models especially Generative Adversarial Networks can easily diverge in low-data setting. To mitigate this issue, we propose a novel implicit data augmentation approach which facilitates stable training and synthesize high-quality samples without need of label information. Specifically, we view the discriminator as a metric embedding of the real data manifold, which offers proper distances between real data points. We then utilize information in the feature space to develop a fully unsupervised and data-driven augmentation method. Experiments on few-shot generation tasks"},"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":"2112.02450","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T23:55:46Z","cross_cats_sorted":[],"title_canon_sha256":"c0f1e6e884d79cb8850ee74b80b7b4b243aae01f164b982598e03a9c4c4629da","abstract_canon_sha256":"4060ccea13f60ea6b2c50e8506b9053f0fad27fbfdec48c212f3454d90cf82f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:08.250309Z","signature_b64":"524+SY2PIoiPJrVSaCxd50DD95yOI/xouZY7sF1jYA1ENXmzYK5mdR+LFy/jc7+G5Jr/2dsktGhegURjoESfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c360f496a2c8fdac27ef302bc572dd4dd645ae0d0dc96684b9a2c5d93d8a54cc","last_reissued_at":"2026-07-05T04:40:08.249852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:08.249852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Feature Interpolation for Low-Shot Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibin Hang, Mengyu Dai, Xiaoyang Guo","submitted_at":"2021-12-04T23:55:46Z","abstract_excerpt":"Training of generative models especially Generative Adversarial Networks can easily diverge in low-data setting. To mitigate this issue, we propose a novel implicit data augmentation approach which facilitates stable training and synthesize high-quality samples without need of label information. Specifically, we view the discriminator as a metric embedding of the real data manifold, which offers proper distances between real data points. We then utilize information in the feature space to develop a fully unsupervised and data-driven augmentation method. Experiments on few-shot generation tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02450","kind":"arxiv","version":3},"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/2112.02450/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":"2112.02450","created_at":"2026-07-05T04:40:08.249909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02450v3","created_at":"2026-07-05T04:40:08.249909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02450","created_at":"2026-07-05T04:40:08.249909+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNQPJFVCZD62","created_at":"2026-07-05T04:40:08.249909+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNQPJFVCZD62YJ7P","created_at":"2026-07-05T04:40:08.249909+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNQPJFVC","created_at":"2026-07-05T04:40:08.249909+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/YNQPJFVCZD62YJ7PGAV4K4W5JX","json":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX.json","graph_json":"https://pith.science/api/pith-number/YNQPJFVCZD62YJ7PGAV4K4W5JX/graph.json","events_json":"https://pith.science/api/pith-number/YNQPJFVCZD62YJ7PGAV4K4W5JX/events.json","paper":"https://pith.science/paper/YNQPJFVC"},"agent_actions":{"view_html":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX","download_json":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX.json","view_paper":"https://pith.science/paper/YNQPJFVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02450&json=true","fetch_graph":"https://pith.science/api/pith-number/YNQPJFVCZD62YJ7PGAV4K4W5JX/graph.json","fetch_events":"https://pith.science/api/pith-number/YNQPJFVCZD62YJ7PGAV4K4W5JX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX/action/storage_attestation","attest_author":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX/action/author_attestation","sign_citation":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX/action/citation_signature","submit_replication":"https://pith.science/pith/YNQPJFVCZD62YJ7PGAV4K4W5JX/action/replication_record"}},"created_at":"2026-07-05T04:40:08.249909+00:00","updated_at":"2026-07-05T04:40:08.249909+00:00"}