# Exploring Self-Attention for Visual Intersection Classification

arXiv: https://arxiv.org/abs/2203.13977 · HTML: https://mlsanity.com/paper/2203.13977/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 47 references that are in the map.
- First posted on arXiv 26 Mar 2022.

## Builds on (most cited first, 10 of 10)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Assessment of Deep Convolutional Neural Networks for Road Surface Classification](https://mlsanity.com/paper/1804.08872/) (2018)
- [An Unsupervised Random Forest Clustering Technique for Automatic Traffic Scenario Categorization](https://mlsanity.com/paper/2004.02121/) (2020)
- [Detecting Traffic Lights by Single Shot Detection](https://mlsanity.com/paper/1805.02523/) (2018)
- [Self-localization from Images with Small Overlap](https://mlsanity.com/paper/1603.00993/) (2016)
- [Momo: Monocular Motion Estimation on Manifolds](https://mlsanity.com/paper/1708.00397/) (2017)
- [Use of First and Third Person Views for Deep Intersection Classification](https://mlsanity.com/paper/1901.07446/) (2019)

## Abstract (arXiv)

In robot vision, self-attention has recently emerged as a technique for capturing non-local contexts. In this study, we introduced a self-attention mechanism into the intersection recognition system as a method to capture the non-local contexts behind the scenes. An intersection classification system comprises two distinctive modules: (a) a first-person vision (FPV) module, which uses a short egocentric view sequence as the intersection is passed, and (b) a third-person vision (TPV) module, which uses a single view immediately before entering the intersection. The self-attention mechanism is effective in the TPV module because most parts of the local pattern (e.g., road edges, buildings, and sky) are similar to each other, and thus the use of a non-local context (e.g., the angle between two diagonal corners around an intersection) would be effective. This study makes three major contributions. First, we proposed a self-attention-based approach for intersection classification using TPVs. Second, we presented a practical system in which a self-attention-based TPV module is combined with an FPV module to improve the overall recognition performance. Finally, experiments using the public KITTI dataset show that the above self-attention-based system outperforms conventional recognition based on local patterns and recognition based on convolution operations.