papers AI Learner
The Github is limit! Click to go to the new site.

Semantically Interpretable and Controllable Filter Sets

2019-02-17
Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib

Abstract

In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion. Each semantic filter learns a visually interpretable local structure in conjunction with other filters. The significance of learning these interpretable filter sets is demonstrated on two contrasting applications. The first application is image recognition under progressive decolorization, in which recognition algorithms should be color-insensitive to achieve a robust performance. The second application is image quality assessment where objective methods should be sensitive to color degradations. In the proposed work, the sensitivity and lack thereof are controlled by weighing the semantic filters based on the local structures they represent. To validate the proposed approach, we utilize the CURE-TSR dataset for image recognition and the TID 2013 dataset for image quality assessment. We show that the proposed semantic filter set achieves state-of-the-art performances in both datasets while maintaining its robustness across progressive distortions.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.06334

PDF

http://arxiv.org/pdf/1902.06334


Similar Posts

Comments