Deep Learning for Scene Classification: A Survey

Abstract

Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challenging problem in computer vision. The rise of large-scale datasets, which constitute the corresponding dense sampling of diverse real-world scenes, and the renaissance of deep learning techniques, which learn powerful feature representations directly from big raw data, have been bringing remarkable progress in the field of scene representation and classification. To help researchers master needed advances in this field, the goal of this paper is to provide a comprehensive survey of recent achievements in scene classification using deep learning. More than 200 major publications are included in this survey covering different aspects of scene classification, including challenges, benchmark datasets, taxonomy, and quantitative performance comparisons of the reviewed methods. In retrospect of what has been achieved so far, this paper is also concluded with a list of promising research opportunities.

References in corpus (12)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Learning in Neural Networks: An Overview
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• How transferable are features in deep neural networks?
• Learning Transferable Features with Deep Adaptation Networks
• Learning to Navigate in Complex Environments
• The Unreasonable Effectiveness of Deep Learning in Artificial Intelligence
• Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors
• Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs
• Deep Spatial Pyramid: The Devil is Once Again in the Details
• Object-Level Context Modeling For Scene Classification with Context-CNN
• Joint Spatial and Layer Attention for Convolutional Networks