Shedding Light on Darkness: Enhancing Object Detection Robustness with Synthetic Perturbations for Real-world Challenges
Jun 1, 2023
Improving Object Detection Robustness against Natural Perturbations through Synthetic Data Augmentation
Jun 1, 2023
Enhancing object detection robustness: A synthetic and natural perturbation approach
Apr 1, 2023
URSABench: A System for Comprehensive Benchmarking of Bayesian Deep Neural Network Models and Inference Methods
URSABench is an open-source benchmarking suite for assessing Bayesian deep learning models and inference methods, focusing on uncertainty quantification, robustness, scalability, and accuracy in classification tasks for both server and edge GPUs.
Apr 1, 2022
Are Graph Neural Networks Miscalibrated?
May 1, 2019