A Discriminative Representation of Convolutional Features for Indoor Scene Recognition

TL;DR

This paper introduces a novel discriminative feature transformation for convolutional features, improving indoor scene recognition by leveraging rich mid-level features and a large-scale object dataset.

Contribution

It proposes a new feature transformation method that enhances discriminative power for indoor scene recognition, utilizing a large dataset of object categories.

Findings

Significant performance improvement over previous methods

Effective encoding of object categories in scene recognition

Robustness to intra-class variations in indoor scenes

Abstract

Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities. This paper presents a novel approach which exploits rich mid-level convolutional features to categorize indoor scenes. Traditionally used convolutional features preserve the global spatial structure, which is a desirable property for general object recognition. However, we argue that this structuredness is not much helpful when we have large variations in scene layouts, e.g., in indoor scenes. We propose to transform the structured convolutional activations to another highly discriminative feature space. The representation in the transformed space not only incorporates the discriminative aspects of the target dataset, but it also encodes the features in terms of the general object categories that are present in indoor scenes. To this end, we introduce a new large-scale dataset of 1300 object categories which are commonly present in indoor scenes. Our proposed approach achieves a significant performance boost over previous state of the art approaches on five major scene classification datasets.