Understand scene categories by objects: A semantic regularized scene classifier using Convolutional Neural Networks

By Yiyi Liao, Sarath Kodagoda, Yue Wang, Lei Shi, Y. Liu. 2015

111 citations recorded by the source corpus.

Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene understanding, particularly in robotics applications. As scene images have larger diversity than the iconic object images, it is more challenging for deep learning methods to automatically learn features from scene images with less samples. Inspired by human scene understanding based on object knowledge, we address the problem of scene classification by encouraging deep neural networks to incorporate object-level information. This is implemented with a regularization of semantic segmentation. With only 5 thousand training images, as opposed to 2.5 million images, we show the proposed deep architecture achieves superior scene classification results to the state-of-the-art on a publicly available SUN RGB-D dataset. In addition, performance of semantic segmentation, the regularizer, also reaches a new record with refinement derived from predicted scene labels. Finally, we apply our model trained on SUN RGB-D dataset to a set of images captured in our university using a mobile robot, demonstrating the generalization ability of the proposed algorithm.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (2017, methodology): “Many focus on semantic tasks, such as classification and semantic segmentation [30] or classification and detection [38].”
Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, methodology): “It showed that networks trained for semantic place categorization (Zhou et al., 2014; Liao et al., 2016b) were more effective than those trained for object detection (Girshick et al., 2014).”