Generalized Deep Image to Image Regression

@article{Santhanam2017GeneralizedDI,
  title={Generalized Deep Image to Image Regression},
  author={Venkataraman Santhanam and Vlad I. Morariu and Larry S. Davis},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={5395-5405}
}
We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any further machinery. Our proposed architecture, the Recursively Branched Deconvolutional Network (RBDN), develops a cheap multi-context image representation very early on using an efficient recursive branching scheme with extensive parameter sharing and learnable upsampling. This multi-context representation is subjected to a highly non-linear… Expand
Dense Activation Network for Image Denoising
TLDR
A dense activation network (DAN) with a dense activation block (DAB) consisting of a dense information fusion (DIF) net and a spatial activation (SA) net that adaptively recalibrates features by considering the spatial relationships within channels. Expand
Deep Multiscale Detail Networks for Multiband Spectral Image Sharpening
TLDR
A new deep detail network architecture with grouped multiscale dilated convolutions to sharpen images contain multiband spectral information to improve generalization to new satellites, and is able to generalize different satellite images without the need for parameter tuning. Expand
Learning a Deep Convolutional Network for Subband Image Denoising
TLDR
A new convolutional neural network for subband image denoising and name it SDCNN, which incorporates frequency information with spatial context and enlarges the receptive field without increasing depth or sacrificing efficiency of network. Expand
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising
TLDR
The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance, and enjoys several desirable properties, including the ability to handle a wide range of noise levels effectively with a single network. Expand
Multi-Level Wavelet Convolutional Neural Networks
TLDR
A novel multi-level wavelet CNN (MWCNN) model is proposed to achieve a better tradeoff between receptive field size and computational efficiency and demonstrates the effectiveness of the proposed MWCNN for tasks, such as image denoising, single image super-resolution, JPEG image artifacts removal, and object classification. Expand
Convolutional Neural Networks for Image Denoising and Restoration
TLDR
This chapter provides a gentle introduction of CNN-based denoising methods by presenting and answering the following three questions: can the authors learn a deep CNN for effective image Denoising, can a single CNN for fast and flexible non-blind image denoised, and can they leverage CNN denoiser prior to versatile image restoration tasks. Expand
Stacked lossless deconvolutional network for remote sensing image restoration
TLDR
Experimental comparisons on various restoration tasks, including super-resolution, denoising, and compression artifact reduction, demonstrate the superiority of the proposed method over state-of-the-art methods both qualitatively and quantitatively. Expand
Visualized Insights into the Optimization Landscape of Fully Convolutional Networks
TLDR
This work investigates the cause and provides experiments to shows that the skip-layer connections in FCN can promote flat optimization landscape, which is well known to generalize better, and explores the relationship between the models generalization ability and loss surface under different batch sizes. Expand
Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework
TLDR
A new degradation model with a novel update scheme is designed to integrate the deep neural network as the prior within the plug-and-play model and outperforms the state-of-the-art in terms of PSNR and SSIM score without extra training process. Expand
Conditional Score Matching for Image to Image Regression
  • Hao Xin, M. Zhu
  • Computer Science
  • 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)
  • 2020
TLDR
The proposed model surpasses other purely generative models and achieves comparable performance to some end-to-end regression methods and demonstrates remarkable generalization ability which further demonstrates the advantage of the proposed conditional score matching framework. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TLDR
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. Expand
Let there be color!
TLDR
A novel technique to automatically colorize grayscale images that combines both global priors and local image features and can process images of any resolution, unlike most existing approaches based on CNN. Expand
Natural Image Denoising with Convolutional Networks
TLDR
An approach to low-level vision is presented that combines the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models to avoid computational difficulties in MRF approaches that arise from probabilistic learning and inference. Expand
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
TLDR
Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet. Expand
Adaptive Multi-Column Deep Neural Networks with Application to Robust Image Denoising
TLDR
The adaptive multi-column stacked sparse denoising autoencoder (AMC-SSDA) is presented, a novel technique of combining multiple SSDAs by computing optimal column weights via solving a nonlinear optimization program and training a separate network to predict the optimal weights. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Fully Convolutional Networks for Semantic Segmentation
TLDR
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Expand
Image Denoising and Inpainting with Deep Neural Networks
TLDR
A novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA) is presented and can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random. Expand
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
TLDR
This work considers image transformation problems, and proposes the use of perceptual loss functions for training feed-forward networks for image transformation tasks, and shows results on image style transfer, where aFeed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time. Expand
Learning Deconvolution Network for Semantic Segmentation
TLDR
A novel semantic segmentation algorithm by learning a deep deconvolution network on top of the convolutional layers adopted from VGG 16-layer net, which demonstrates outstanding performance in PASCAL VOC 2012 dataset. Expand
...
1
2
3
4
5
...