# Fast and Efficient Scene Categorization for Autonomous Driving using VAEs

arXiv: https://arxiv.org/abs/2210.14981 · HTML: https://mlsanity.com/paper/2210.14981/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 12 of 12)

- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [Tighter Variational Bounds are Not Necessarily Better](https://mlsanity.com/paper/1802.04537/) (2018)
- [Does computer vision matter for action?](https://mlsanity.com/paper/1905.12887/) (2019)
- [A Discriminative Representation of Convolutional Features for Indoor Scene Recognition](https://mlsanity.com/paper/1506.05196/) (2015)
- [OdoViz: A 3D Odometry Visualization and Processing Tool](https://mlsanity.com/paper/2107.07557/) (2021)

## Built on by (most cited first, 1 of 1)

- [Scalable and Efficient Hierarchical Visual Topological Mapping](https://mlsanity.com/paper/2404.05023/) (2024)

## Abstract (arXiv)

Scene categorization is a useful precursor task that provides prior knowledge for many advanced computer vision tasks with a broad range of applications in content-based image indexing and retrieval systems. Despite the success of data driven approaches in the field of computer vision such as object detection, semantic segmentation, etc., their application in learning high-level features for scene recognition has not achieved the same level of success. We propose to generate a fast and efficient intermediate interpretable generalized global descriptor that captures coarse features from the image and use a classification head to map the descriptors to 3 scene categories: Rural, Urban and Suburban. We train a Variational Autoencoder in an unsupervised manner and map images to a constrained multi-dimensional latent space and use the latent vectors as compact embeddings that serve as global descriptors for images. The experimental results evidence that the VAE latent vectors capture coarse information from the image, supporting their usage as global descriptors. The proposed global descriptor is very compact with an embedding length of 128, significantly faster to compute, and is robust to seasonal and illuminational changes, while capturing sufficient scene information required for scene categorization.