Classification-Driven Dynamic Image Enhancement
Classification-Driven Dynamic Image Enhancement
复制标题
DOI：
10.1109/cvpr.2018.00424
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
Vivek Sharma;Ali Diba;D. Neven;M. S. Brown;L. Gool;R. Stiefelhagen
中科院分区：
文献类型：
--
作者：
Vivek Sharma;Ali Diba;D. Neven;M. S. Brown;L. Gool;R. Stiefelhagen
卷积神经网络依靠图像的纹理和结构作为判别特征对图像内容进行分类。图像增强技术可以用作预处理步骤，以帮助提高整体图像质量，从而提高CNN的整体有效性。然而，现有的图像增强方法旨在提高人类观察者的图像感知质量。在本文中，我们感兴趣的是学习可以模拟图像增强和恢复的cnn，但总体目标是提高图像分类，而不一定是人类感知。为此，我们提出了一个统一的CNN架构，该架构使用一系列增强滤波器，可以通过端到端动态滤波器学习来增强图像特定的细节。我们在四个具有挑战性的细粒度、对象、场景和纹理分类基准数据集（CUB-200-2011、PASCAL-VOC2007、MIT-Indoor和DTD）上证明了该策略的有效性。在实验中，我们提出的增强方法在所有数据集上都显示出令人满意的结果。此外，我们的方法能够提高所有通用CNN架构的性能。
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.