Classification-Denoising Networks
Image classification and denoising suffer from complementary issues of lack of robustness or partially ignoring conditioning information. We argue that they can be alleviated by unifying both tasks through a model of the joint probability of (noisy) images and class labels. Classification is performed with a forward pass followed by conditioning. Using the Tweedie-Miyasawa formula, we evaluate the denoising function with the score, which can be computed by marginalization and back-propagation. The training objective is then a combination of cross-entropy loss and denoising score matching loss integrated over noise levels. Numerical experiments on CIFAR-10 and ImageNet show competitive classification and denoising performance compared to reference deep convolutional classifiers/denoisers, and significantly improves efficiency compared to previous joint approaches. Our model shows an increased robustness to adversarial perturbations compared to a standard discriminative classifier, and allows for a novel interpretation of adversarial gradients as a difference of denoisers.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationDenoisingimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On the Relation between Color Image Denoising and Classification
Large amount of image denoising literature focuses on single channel images and often experimentally validates the proposed methods on tens of images at most. In this paper, we investigate the interaction between denoisi…
ClassificationColor Image DenoisingDenoisingGeneral Classification+2Spectral Denoising for Microphone Classification
In this paper, we propose the use of denoising for microphone classification, to enable its usage for several key application domains that involve noisy conditions. We describe the proposed analysis pipeline and the base…
ClassificationDenoisingContextual Checkerboard Denoise -- A Novel Neural Network-Based Approach for Classification-Aware OCT Image Denoising
In contrast to non-medical image denoising, where enhancing image clarity is the primary goal, medical image denoising warrants preservation of crucial features without introduction of new artifacts. However, many denois…
DenoisingDiagnosticimage-classificationImage Classification+2Pushing Joint Image Denoising and Classification to the Edge
In this paper, we jointly combine image classification and image denoising, aiming to enhance human perception of noisy images captured by edge devices, like low-light security cameras. In such settings, it is important …
ClassificationDenoisingimage-classificationImage Classification+2Adaptive Differential Denoising for Respiratory Sounds Classification
Automated respiratory sound classification faces practical challenges from background noise and insufficient denoising in existing systems. We propose Adaptive Differential Denoising network, that integrates noise suppre…
Audio ClassificationClassificationDenoisingDiagnostic+1