Reducing Bias in Pre-trained Models by Tuning while Penalizing Change

arXiv:2404.12292v1 Announce Type: new
Abstract: Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model. This behavior is especially problematic in critical areas such as autonomous driving or medical decision-making. In these scenarios, new data is often expensive and hard to come by. In this work, we present a method based …

abstract arxiv behavior bias biases change cs.cv data deployment inference pre-trained models retrain training type