Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers

by   Hila Chefer, et al.

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 co-attention 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 co-attention 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 self-attention, (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.


page 1

page 3

page 4

page 5

page 8

page 9

page 10

page 14


Vision Transformers: State of the Art and Research Challenges

Transformers have achieved great success in natural language processing....

Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps

Transformer-based language models significantly advanced the state-of-th...

Transformer Interpretability Beyond Attention Visualization

Self-attention techniques, and specifically Transformers, are dominating...

Centroid Transformers: Learning to Abstract with Attention

Self-attention, as the key block of transformers, is a powerful mechanis...

Fair Comparison between Efficient Attentions

Transformers have been successfully used in various fields and are becom...

Local Attention Graph-based Transformer for Multi-target Genetic Alteration Prediction

Classical multiple instance learning (MIL) methods are often based on th...

Focused Decoding Enables 3D Anatomical Detection by Transformers

Detection Transformers represent end-to-end object detection approaches ...

Code Repositories


[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

view repo