Derek Hoiem

Improving Confidence Estimates for Unfamiliar Examples

2020

Intuitively, unfamiliarity should lead to lack of confidence. In reality, current algorithms often make highly confident yet wrong predictions when faced with relevant but unfamiliar examples. A classifier we trained to recognize gender is 12 …

Comparing Human Object Learning with Deep Neural Networks

2023 · Journal of Vision

One challenge in machine learning is that networks readily forget previously learned information as they encounter new information. For example, a network pre-trained with ImageNet can acquire useful features for classification tasks. However, training it …