No abstract

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and coattention mechanisms. These attention modules also play a role in other computer vision tasks including object detection and image segmentation. Unlike Transformers that only use self-attention, Transformers with coattention require to consider multiple attention maps in parallel in order to highlight the information that is relevant to the prediction in the model's input. In this work, we propose the first method to explain prediction by any Transformer-based architecture, including bi-modal Transformers and Transformers with co-attentions. We provide generic solutions and apply these to the three most commonly used of these architectures: (i) pure selfattention, (ii) self-attention combined with co-attention, and (iii) encoder-decoder attention. We show that our method is superior to all existing methods which are adapted from single modality explainability. Our code is available at: https://github.com/hila-chefer/ Transformer-MM-Explainability.

Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In order to visualize the parts of the image that led to a certain classification, existing methods either rely on the obtained attention maps, or employ heuristic propagation along the attention graph. In this work, we propose a novel way to compute relevancy for Transformer networks. The method assigns local relevance based on the deep Taylor decomposition principle and then propagates these relevancy scores through the layers. This propagation involves attention layers and skip connections, which challenge existing methods. Our solution is based on a specific formulation that is shown to maintain the total relevancy across layers. We benchmark our method on very recent visual Transformer networks, as well as on a text classification problem, and demonstrate a clear advantage over the existing explainability methods. Our code is available at: https://github.com/hila-chefer/ Transformer-Explainability.

Figure 1. Given a pre-trained text-to-image diffusion model (e.g. Stable Diffusion [39]) our method, Attend-and-Excite, guides the generative model to modify the cross-attention values during the image synthesis process to generate images that more faithfully depict the input text prompt. Stable Diffusion alone (top row) struggles to generate multiple objects (e.g. a horse and a dog). However, by incorporating Attend-and-Excite (bottom row) to strengthen the subject tokens (marked in blue), we achieve images that are more semantically faithful with respect to the input text prompts.

No abstract