Source code is made available at https://github.com/ymLeiFDU/LICO.

We directly adopt the official default setting for Atari games. B.2 Minecraft Environment Settings Table 1 outlines how we set up and initialize the environment for each harvest task. Our method is tested in two different biomes: plains and sunflower plains. Both the plains and sunflower plains offer a wider field of view. In Minecraft, the action space is an 8-dimensional multi-discrete space.

Over time, the two branches interact recurrently to build a scene representation from moving fixations.

Building upon Miller's framework of explanations derived from research in multiple

Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability.

We adopted the existing code from Amersfoort et al. to train the DUQ models. DIP/INR and the proposed manifold consistency, it can still be challenging to avoid trivial solutions. However, given the large solution space, this often leads to unrealistic images. For this experiment, we used the CelebA faces dataset and considered the baldness attribute. Figure 1: Examples of counterfactuals generated for the baldness and age attributes using DISC.

Central to models of human visual attention is the saliency map. We propose a hierarchical visual architecture that operates on a saliency map and uses a novel attention mechanism to sequentially focus on salient regions and take additional glimpses within those regions. The architecture is motivated by human visual attention, and is used for multi-label image classification on a novel multiset task, demonstrating that it achieves high precision and recall while localizing objects with its attention. Unlike conventional multi-label image classification models, the model supports multiset prediction due to a reinforcement-learning based training process that allows for arbitrary label permutation and multiple instances per label.