The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …

In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation
criteria have been developed within the research field of explainable artificial intelligence …

Designed to learn long-range interactions on sequential data, transformers continue to show
state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no …

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN
model so that the image can be faithfully reconstructed from the inverted code by the …

Abstract We present Generative Semantic Segmentation (GSS), a generative learning
approach for semantic segmentation. Uniquely, we cast semantic segmentation as an image …

Autoregressive models and their sequential factorization of the data likelihood have recently
demonstrated great potential for image representation and synthesis. Nevertheless, they …

Image classification models can depend on multiple different semantic attributes of the
image. An explanation of the decision of the classifier needs to both discover and visualize …

Self-supervised monocular depth estimation has been widely studied recently. Most of the
work has focused on improving performance on benchmark datasets, such as KITTI, but has …

Disentangled representation learning has been proposed as an approach to learning
general representations even in the absence of, or with limited, supervision. A good general …

Is a geometric model required to synthesize novel views from a single image? Being bound
to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In …