Learning-based methods especially with convolutional neural networks (CNN) are continuously showing superior performance in computer vision applications, ranging from image classification to restoration. For image classification, most existing works focus on very clean images such as images in Caltech-256 and ImageNet datasets. However, in most realistic scenarios, the acquired images may suffer from degradation. One important and interesting problem is to combine image classification and restoration tasks to improve the performance of CNN-based classification networks on degraded images. In this report, we explore the influence of degradation types and levels on four widely-used classification networks, and the use of a restoration network to eliminate the degradation's influence. We also propose a novel method leveraging a fidelity map to calibrate the image features obtained by pre-trained classification networks. We empirically demonstrate that our proposed method consistently outperforms the pre-trained networks under all degradation levels and types with additive white Gaussian noise (AWGN), and it even outperforms the re-trained networks for degraded images under low degradation levels. We also show that the proposed method is a model-agnostic approach that benefits different classification networks. Our results reveal that the proposed method is a promising solution to mitigate the effect caused by image degradation.
翻译:以学习为基础的方法,特别是进化神经网络(CNN),在从图像分类到恢复的计算机视觉应用方面不断显示优异性能,从图像分类到恢复。在图像分类方面,大多数现有作品侧重于非常干净的图像,例如Caltech-256和图像网络数据集中的图像。然而,在大多数现实情况下,获得的图像可能会退化。一个重要和有趣的问题是将图像分类和恢复任务结合起来,以提高CNN的退化图像分类网络在退化图像方面的性能。在本报告中,我们探讨了退化类型和水平对四个广泛使用的分类网络的影响,以及利用恢复网络消除退化的影响。我们还提出了一个创新的方法,利用忠诚图来校准预先培训过的分类网络获得的图像特征。我们的经验证明,我们提出的方法始终超越了所有降解级别和类型的预先培训的网络,与添加的白高尔西噪音(AWGN)相结合。它甚至超越了在低降解水平下对退化图像进行再培训的网络。我们还表明,拟议的方法是一种模型学方法,有利于不同分类网络的退化。我们的结果表明,通过一种有希望的解决方案来减轻不同分类网络的退化。