FACTOR uses counterfactual image perturbations to quantify and suppress attribute-dependent predictions in open-vocabulary object detection, improving robustness on corrupted datasets without any training.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PTA adapts VLMs at test time by maintaining and updating class-specific knowledge prototypes from test samples, achieving higher accuracy than cache-based methods with far less speed loss.
citing papers explorer
-
FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection
FACTOR uses counterfactual image perturbations to quantify and suppress attribute-dependent predictions in open-vocabulary object detection, improving robustness on corrupted datasets without any training.
-
Prototype-Based Test-Time Adaptation of Vision-Language Models
PTA adapts VLMs at test time by maintaining and updating class-specific knowledge prototypes from test samples, achieving higher accuracy than cache-based methods with far less speed loss.