Preprint
Abstract
Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them. The problem is aggravated when images of a particular scene class are notably different. Convolutional Neural Networks (CNNs) have significantly boosted performance in scene recognition, albeit it is still far below from other recognition tasks (e.g., object or image recognition). In this paper, we describe a novel approach for scene recognition based on an end-to-end multi-modal CNN that combines image and context information by means of an attention module. Context information, in the shape of semantic segmentation, is used to gate features extracted from the RGB image by leveraging on information encoded in the semantic representation: the set of scene objects and stuff, and their relative locations. This gating process reinforces the learning of indicative scene content and enhances scene disambiguation by refocusing the receptive fields of the CNN towards them. Experimental results on four publicly available datasets show that the proposed approach outperforms every other state-of-the-art method while significantly reducing the number of network parameters. All the code and data used along this paper is available at https://github.com/vpulab/Semantic-Aware-Scene-RecognitionKeywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Small Object Sensitive Segmentation of Urban Street Scene With Spatial Adjacency Between Object ClassesIEEE Transactions on Image Processing, 2018
- In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization2018
- LG-CNN: From local parts to global discrimination for fine-grained recognitionPattern Recognition, 2017
- Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?Computer Vision and Image Understanding, 2017
- Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene RecognitionIEEE Transactions on Image Processing, 2017
- Learning Deep Features for Discriminative Localization2016
- Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain AdaptationIEEE Transactions on Circuits and Systems for Video Technology, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- CENTRIST: A Visual Descriptor for Scene CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Gist of the Scene2005