AI RESEARCH

FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection

arXiv CS.CV

ArXi:2605.03294v1 Announce Type: new Open-vocabulary object detection often fails under distribution shifts, as it can be misled by spurious correlations between non-causal visual attributes (e.g., brightness, texture) and object categories. Existing test-time adaptation (TTA) methods either depend on costly online optimization or perform global calibration, overlooking the attribute-specific nature of these failures. To address this, we propose FACTOR (counterFACtual