Deep Learning with Inaccurate Training Data for Image Restoration
arXiv:1811.07268
Abstract
In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one is forced to use synthesized paired data to train the deep convolutional neural network (DCNN). However, due to the unavoidable generalization error in statistical learning, the synthetically trained DCNN often performs poorly on real world data. To overcome this problem, we propose a new general training method that can compensate for, to a large extent, the generalization errors of synthetically trained DCNNs.
References in corpus (8)
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
- RENOIR - A Dataset for Real Low-Light Image Noise Reduction
- Real-world Noisy Image Denoising: A New Benchmark
- On learning optimized reaction diffusion processes for effective image restoration
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
- Burst Denoising with Kernel Prediction Networks