TRAR: Routing the Attention Spans in Transformer for Visual Question Answering

By Yiyi Zhou, Tianhe Ren, Chaoyang Zhu, Xiaoshuai Sun, Jianzhuang Liu, Xi-hao Ding, Mingliang Xu, Rongrong Ji. 2021

132 citations recorded by the source corpus.

Due to the superior ability of global dependency modeling, Transformer and its variants have become the primary choice of many vision-and-language tasks. However, in tasks like Visual Question Answering (VQA) and Referring Expression Comprehension (REC), the multimodal prediction often requires visual information from macro- to micro-views. Therefore, how to dynamically schedule the global and local dependency modeling in Transformer has become an emerging issue. In this paper, we propose an example-dependent routing scheme called TRAnsformer Routing (TRAR) to address this issue1. Specifically, in TRAR, each visual Transformer layer is equipped with a routing module with different attention spans. The model can dynamically select the corresponding attentions based on the output of the previous inference step, so as to formulate the optimal routing path for each example. Notably, with careful designs, TRAR can reduce the additional computation and memory overhead to almost negligible. To validate TRAR, we conduct extensive experiments on five benchmark datasets of VQA and REC, and achieve superior performance gains than the standard Transformers and a bunch of state-of-the-art methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Hongsheng Li
5. Guanglu Song
6. Shengju Qian
7. Zhuofan Zong
8. Hao Shao

In Computer Vision and Pattern Recognition

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Yu Liu
5. Guanglu Song
6. Hao Shao
7. Hongsheng Li
8. Shengju Qian

Citations in the corpus

• Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (2022, methodology): “Transformer models are now widely applied into visual question answering [82], object detection [83], segmentation [84], video understanding [85], etc.”
• Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning (2024, background): “Trar [78] proposes a routing module to dynamically select informative regions based on the attention map.”