Abstract: Explanation supervision is a technique in which the model is guided by human-generated explanations during training. This technique aims to improve the predictability of the model by ...

We introduce an low-biased general annotated dataset generation (lbGen) framework which directly generates low-biased images with category annotations. We find that pre-training on our generated ...

Abstract: Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance. However, the process of collecting and labeling such data can be ...