W Cai, R Encarnacion, B Chern… - Proceedings of the …, 2022 - dl.acm.org
In domains ranging from computer vision to natural language processing, machine learning models have been shown to exhibit stark disparities, often performing worse for members of …
RS Stone, N Ravikumar, AJ Bulpitt… - Proceedings of the …, 2022 - openaccess.thecvf.com
Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge …
We examine a simple stochastic strategy for adapting well-known single-point acquisition functions to allow batch active learning. Unlike acquiring the top-K points from the pool set …
R Elie, C Hillairet, F Hu, M Juillard - arXiv preprint arXiv:2112.09466, 2021 - arxiv.org
This paper addresses and solves some challenges in the adoption of machine learning in insurance with the democratization of model deployment. The first challenge is reducing the …
Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset …
TH Wu, HT Su, ST Chen… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We introduce a new learning framework, Fair Robust Active Learning (FRAL), generalizing conventional active learning to fair and adversarial robust scenarios. This framework …
Improving the accuracy-fairness frontier of deep neural network (DNN) models is an important problem. Uncertainty-based active learning (AL) can potentially improve the …
A Kirsch - arXiv preprint arXiv:2401.04305, 2024 - arxiv.org
At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset …
RS Stone, N Ravikumar, AJ Bulpitt… - arXiv preprint arXiv …, 2023 - arxiv.org
The fairness of a deep neural network is strongly affected by dataset bias and spurious correlations, both of which are usually present in modern feature-rich and complex visual …