5 papers
Energy-Based Open-Set Active Learning for Object Classification
Zongyao Lyu, William J. Beksi
Active learning (AL) has emerged as a crucial methodology for minimizing labeling costs in deep learning by selecting the most valuable samples from a pool of unlabeled data for an…
ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control
Lingling Chen, Zongyao Lyu, William J. Beksi
Vision-language-action (VLA) models have emerged as generalist robotic controllers capable of mapping visual observations and natural language instructions to continuous action seq…
Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling
Zongyao Lyu, William J. Beksi
Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variation…
Evaluating Uncertainty Calibration for Open-Set Recognition
Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
Despite achieving enormous success in predictive accuracy for visual classification problems, deep neural networks (DNNs) suffer from providing overconfident probabilities on out-o…
An Uncertainty Estimation Framework for Probabilistic Object Detection
Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection. Quantifying uncertainty is critical in real-world robotic…