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

• URL: http://arxiv.org/abs/2103.15679v1
• Date: Mon, 29 Mar 2021 15:03:11 GMT
• Title: Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
• Authors: Hila Chefer, Shir Gur, and Lior Wolf
• Abstract summary: We propose the first method to explain prediction by any Transformer-based architecture. Our method is superior to all existing methods which are adapted from single modality explainability.
• Score: 78.26411729589526
• License: http://creativecommons.org/licenses/by/4.0/
• 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 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.

Related papers

• DAPE V2: Process Attention Score as Feature Map for Length Extrapolation [63.87956583202729]
  We conceptualize attention as a feature map and apply the convolution operator to mimic the processing methods in computer vision. The novel insight, which can be adapted to various attention-related models, reveals that the current Transformer architecture has the potential for further evolution.
  arXiv  Detail & Related papers  (2024-10-07T07:21:49Z)
• AttentionViz: A Global View of Transformer Attention [60.82904477362676]
  We present a new visualization technique designed to help researchers understand the self-attention mechanism in transformers. The main idea behind our method is to visualize a joint embedding of the query and key vectors used by transformer models to compute attention. We create an interactive visualization tool, AttentionViz, based on these joint query-key embeddings.
  arXiv  Detail & Related papers  (2023-05-04T23:46:49Z)
• Holistically Explainable Vision Transformers [136.27303006772294]
  We propose B-cos transformers, which inherently provide holistic explanations for their decisions. Specifically, we formulate each model component - such as the multi-layer perceptrons, attention layers, and the tokenisation module - to be dynamic linear. We apply our proposed design to Vision Transformers (ViTs) and show that the resulting models, dubbed Bcos-ViTs, are highly interpretable and perform competitively to baseline ViTs.
  arXiv  Detail & Related papers  (2023-01-20T16:45:34Z)
• What Makes for Good Tokenizers in Vision Transformer? [62.44987486771936]
  transformers are capable of extracting their pairwise relationships using self-attention. What makes for a good tokenizer has not been well understood in computer vision. Modulation across Tokens (MoTo) incorporates inter-token modeling capability through normalization. Regularization objective TokenProp is embraced in the standard training regime.
  arXiv  Detail & Related papers  (2022-12-21T15:51:43Z)
• Multi-manifold Attention for Vision Transformers [12.862540139118073]
  Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks. A novel attention mechanism, called multi-manifold multihead attention, is proposed in this work to substitute the vanilla self-attention of a Transformer.
  arXiv  Detail & Related papers  (2022-07-18T12:53:53Z)
• Evolving Attention with Residual Convolutions [29.305149185821882]
  We propose a novel mechanism based on evolving attention to improve the performance of transformers. The proposed attention mechanism achieves significant performance improvement over various state-of-the-art models for multiple tasks.
  arXiv  Detail & Related papers  (2021-02-20T15:24:06Z)
• Learning Hard Retrieval Decoder Attention for Transformers [69.40942736249397]
  Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. We show that our hard retrieval attention mechanism is 1.43 times faster in decoding.
  arXiv  Detail & Related papers  (2020-09-30T13:18:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.