Energy-based model with covariance regularization computes normalized posteriors for linear inverse problems without retraining, enabling adaptive sampling and blind estimation on image datasets.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Learning Normalized Energy Models for Linear Inverse Problems
Energy-based model with covariance regularization computes normalized posteriors for linear inverse problems without retraining, enabling adaptive sampling and blind estimation on image datasets.
-
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.