{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M3SXF6MELECH35QUXEYNVTJAZW","short_pith_number":"pith:M3SXF6ME","schema_version":"1.0","canonical_sha256":"66e572f98459047df614b930dacd20cd97a6f5e653f5cdf1cccab273968d52d7","source":{"kind":"arxiv","id":"2605.29539","version":1},"attestation_state":"computed","paper":{"title":"GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiacong Liu, Shu Luo, Yaze Zhao, Yikai Qin, Yixiong Zou, Yongwei Jiang","submitted_at":"2026-05-28T07:53:40Z","abstract_excerpt":"Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to sparse single-instance annotations, and severe overfitting under extremely limited target-domain samples. To address these issues, this paper proposes GiPL, an efficient two-branch training framework.In the first branch, we design an iterative pseudo-label self-training paradigm, which performs zero-shot inference on the support set to generate reliable pseudo-"},"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":"2605.29539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T07:53:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe05a79b2584afceb3a9afcbb0265ce1e61b7a25eca5892a3242d78e6e70f5e5","abstract_canon_sha256":"1cfc098edf4f45da2a34b32579e95a1453059c7ed9014490003cfc21d778bc5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:46.003187Z","signature_b64":"4MKG/i4kKmTxYmRUe84jIHNd9qu4TlQL/uX4sIiqb5lZrRv2J5Hq/Oqy4tGg/FcKLXQaN+rlFiPSp7xHC4O9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e572f98459047df614b930dacd20cd97a6f5e653f5cdf1cccab273968d52d7","last_reissued_at":"2026-05-29T01:05:46.002436Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:46.002436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiacong Liu, Shu Luo, Yaze Zhao, Yikai Qin, Yixiong Zou, Yongwei Jiang","submitted_at":"2026-05-28T07:53:40Z","abstract_excerpt":"Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to sparse single-instance annotations, and severe overfitting under extremely limited target-domain samples. To address these issues, this paper proposes GiPL, an efficient two-branch training framework.In the first branch, we design an iterative pseudo-label self-training paradigm, which performs zero-shot inference on the support set to generate reliable pseudo-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29539","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/2605.29539/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":"2605.29539","created_at":"2026-05-29T01:05:46.002562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29539v1","created_at":"2026-05-29T01:05:46.002562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29539","created_at":"2026-05-29T01:05:46.002562+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3SXF6MELECH","created_at":"2026-05-29T01:05:46.002562+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3SXF6MELECH35QU","created_at":"2026-05-29T01:05:46.002562+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3SXF6ME","created_at":"2026-05-29T01:05:46.002562+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/M3SXF6MELECH35QUXEYNVTJAZW","json":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW.json","graph_json":"https://pith.science/api/pith-number/M3SXF6MELECH35QUXEYNVTJAZW/graph.json","events_json":"https://pith.science/api/pith-number/M3SXF6MELECH35QUXEYNVTJAZW/events.json","paper":"https://pith.science/paper/M3SXF6ME"},"agent_actions":{"view_html":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW","download_json":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW.json","view_paper":"https://pith.science/paper/M3SXF6ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29539&json=true","fetch_graph":"https://pith.science/api/pith-number/M3SXF6MELECH35QUXEYNVTJAZW/graph.json","fetch_events":"https://pith.science/api/pith-number/M3SXF6MELECH35QUXEYNVTJAZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW/action/storage_attestation","attest_author":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW/action/author_attestation","sign_citation":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW/action/citation_signature","submit_replication":"https://pith.science/pith/M3SXF6MELECH35QUXEYNVTJAZW/action/replication_record"}},"created_at":"2026-05-29T01:05:46.002562+00:00","updated_at":"2026-05-29T01:05:46.002562+00:00"}