Scene Categorization with Spectral Features

Salman H. Khan, Munawar Hayat, Fatih Porikli

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

22 Citations (Scopus)


Spectral signatures of natural scenes were earlier found to be distinctive for different scene types with varying spatial envelope properties such as openness, naturalness, ruggedness, and symmetry. Recently, such handcrafted features have been outclassed by deep learning based representations. This paper proposes a novel spectral description of convolution features, implemented efficiently as a unitary transformation within deep network architectures. To the best of our knowledge, this is the first attempt to use deep learning based spectral features explicitly for image classification task. We show that the spectral transformation decorrelates convolutional activations, which reduces co-adaptation between feature detections, thus acts as an effective regularizer. Our approach achieves significant improvements on three large-scale scene-centric datasets (MIT-67, SUN-397, and Places-205). Furthermore, we evaluated the proposed approach on the attribute detection task where its superior performance manifests its relevance to semantically meaningful characteristics of natural scenes.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages11
ISBN (Electronic)9781538610329
ISBN (Print)9781538610336
Publication statusPublished - 22 Dec 2017
Event16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy
Duration: 22 Oct 201729 Oct 2017

Publication series

NameProceedings of the IEEE International Conference on Computer Vision


Conference16th IEEE International Conference on Computer Vision, ICCV 2017


Dive into the research topics of 'Scene Categorization with Spectral Features'. Together they form a unique fingerprint.

Cite this