Classification Driven Dynamic Image Enhancement

TL;DR

This paper introduces a CNN-based image enhancement method that dynamically learns filters to improve classification accuracy across various challenging datasets, focusing on task-specific enhancement rather than perceptual quality.

Contribution

It proposes a unified CNN architecture with end-to-end dynamic filter learning tailored for enhancing images to boost classification performance.

Findings

Improves classification accuracy on four benchmark datasets.

Enhances performance across various CNN architectures.

Demonstrates effectiveness in fine-grained, object, scene, and texture classification.

Abstract

Convolutional neural networks rely on image texture and structure to serve as discriminative features to classify the image content. Image enhancement techniques can be used as preprocessing steps to help improve the overall image quality and in turn improve the overall effectiveness of a CNN. Existing image enhancement methods, however, are designed to improve the perceptual quality of an image for a human observer. In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception. To this end, we present a unified CNN architecture that uses a range of enhancement filters that can enhance image-specific details via end-to-end dynamic filter learning. We demonstrate the effectiveness of this strategy on four challenging benchmark datasets for fine-grained, object, scene, and texture classification: CUB-200-2011, PASCAL-VOC2007, MIT-Indoor, and DTD. Experiments using our proposed enhancement show promising results on all the datasets. In addition, our approach is capable of improving the performance of all generic CNN architectures.