# FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition

arXiv: https://arxiv.org/abs/1907.07570 · HTML: https://mlsanity.com/paper/1907.07570/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [Deep Learning for Scene Classification: A Survey](https://mlsanity.com/paper/2101.10531/) (2021)
- [Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps](https://mlsanity.com/paper/2104.12294/) (2021)
- [Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models](https://mlsanity.com/paper/2505.06621/) (2025)
- [Scene Retrieval for Contextual Visual Mapping](https://mlsanity.com/paper/2102.12728/) (2021)
- [Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks](https://mlsanity.com/paper/2107.11187/) (2021)
- [When & How to Transfer with Transfer Learning](https://mlsanity.com/paper/2211.04347/) (2022)
- [Designing Deep Networks for Scene Recognition](https://mlsanity.com/paper/2303.07402/) (2023)
- [Exploiting Object-based and Segmentation-based Semantic Features for Deep Learning-based Indoor Scene Classification](https://mlsanity.com/paper/2404.07739/) (2024)

## Abstract (arXiv)

Scene recognition is an image recognition problem aimed at predicting the category of the place at which the image is taken. In this paper, a new scene recognition method using the convolutional neural network (CNN) is proposed. The proposed method is based on the fusion of the object and the scene information in the given image and the CNN framework is named as FOS (fusion of object and scene) Net. In addition, a new loss named scene coherence loss (SCL) is developed to train the FOSNet and to improve the scene recognition performance. The proposed SCL is based on the unique traits of the scene that the 'sceneness' spreads and the scene class does not change all over the image. The proposed FOSNet was experimented with three most popular scene recognition datasets, and their state-of-the-art performance is obtained in two sets: 60.14% on Places 2 and 90.37% on MIT indoor 67. The second highest performance of 77.28% is obtained on SUN 397.