{"paper":{"title":"VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A frozen vision foundation model supplies stability priors that cut missed detections in single-domain object detectors facing unseen conditions.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Wan, Ningnan Guo, Ruize Han, Song Wang, Wei Feng, Yupeng Zhang","submitted_at":"2026-04-23T10:04:36Z","abstract_excerpt":"Real-world weather, illumination, and imaging variations often induce severe domain shifts, degrading single-source detectors in unseen environments. Existing single-domain generalized object detection (SDGOD) methods mainly rely on data augmentation or domain-invariant learning, while largely overlooking how domain shift disrupts detector prediction stability. Through analytical experiments, we find that performance degradation is mainly dominated by increasing missed detections. Further analysis shows that this phenomenon stems from reduced cross-domain stability in DETR-style detectors: dom"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments show that the proposed method consistently outperforms existing SOTA methods on standard SDGOD benchmarks and two mainstream DETR-based detectors, demonstrating its effectiveness, robustness, and generality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the analytical finding of missed-detection dominance and reduced relational stability generalizes beyond the tested conditions, and that a frozen VFM supplies transferable stability priors without introducing new failure modes in the detector.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VFM⁴SDG uses a frozen vision foundation model to inject cross-domain stability priors into both the encoding and decoding stages of object detectors, reducing missed detections in unseen environments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A frozen vision foundation model supplies stability priors that cut missed detections in single-domain object detectors facing unseen conditions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a12b90341f49f14022fa5ee2ba889d713b3f03bcd6d2073ddd59b45923fdf8df"},"source":{"id":"2604.21502","kind":"arxiv","version":2},"verdict":{"id":"70418311-4564-4ecd-b599-3d96adab6db8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T21:34:41.991160Z","strongest_claim":"Extensive experiments show that the proposed method consistently outperforms existing SOTA methods on standard SDGOD benchmarks and two mainstream DETR-based detectors, demonstrating its effectiveness, robustness, and generality.","one_line_summary":"VFM⁴SDG uses a frozen vision foundation model to inject cross-domain stability priors into both the encoding and decoding stages of object detectors, reducing missed detections in unseen environments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the analytical finding of missed-detection dominance and reduced relational stability generalizes beyond the tested conditions, and that a frozen VFM supplies transferable stability priors without introducing new failure modes in the detector.","pith_extraction_headline":"A frozen vision foundation model supplies stability priors that cut missed detections in single-domain object detectors facing unseen conditions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.21502/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T12:40:03.533598Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T00:56:43.055324Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9d8bab188a790cec4ba2cd412586d1f478fc67509841300433cbf244cfd4deaa"},"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"}