NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

Chen, Yunchun; Gao, Chen; Robb, Esther; Huang, Jia-Bin

doi:10.1007/978-3-030-58523-5_26

“…Design of Architecture Search Space: The intrinsic capability of an evolutionary DNN construction method heavily depends on the search space, which is often manually specified. Recently, there emerges a growing interest in automatically designing the search space of model architecture [200]- [202]. On the one hand, a simpler search space may facilitate the optimization process carried out therein.…”

Section: Trendsmentioning

confidence: 99%

A Survey on Evolutionary Construction of Deep Neural Networks

Xun

¹

,

Qin

²

,

Gong

³

et al. 2021

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

Automated construction of deep neural networks (DNNs) has become a research hot spot nowadays because DNN's performance is heavily influenced by its architecture and parameters, which are highly task-dependent, but it is notoriously difficult to find the most appropriate DNN in terms of architecture and parameters to best solve a given task. In this work, we provide an insight into the automated DNN construction process by formulating it into a multilevel multiobjective large-scale optimization problem with constraints, where the nonconvex, nondifferentiable, and black-box nature of this problem make evolutionary algorithms (EAs) to stand out as a promising solver. Then, we give a systematical review of existing evolutionary DNN construction techniques from different aspects of this optimization problem and analyze the pros and cons of using EA-based methods in each aspect. This work aims to help DNN researchers to better understand why, where, and how to utilize EAs for automated DNN construction and meanwhile, help EA researchers to better understand the task of automated DNN construction so that they may focus more on EA-favored optimization scenarios to devise more effective techniques.

show abstract

“…The output at the first iteration contains randomization due to random code vector z and the optimizer iteratively optimizes neural network's parameters θ for the given input image using backpropagation. It has been shown in the literature [19], [36] that the choice of neural network architectures has a direct impact on the performance, e.g., we can design/handcraft a particular neural network architecture for modeling a specific image [21]. This serves as a solution space when modeling images using untrained neural networks priors.…”

Section: Untrained and Pretrained Cdipsmentioning

confidence: 99%

Single-Shot Retinal Image Enhancement Using Untrained and Pretrained Neural Networks Priors Integrated with Analytical Image Priors

Qayyum¹,

Sultani²,

Shamshad³

et al. 2021

Preprint

View full text Add to dashboard Cite

Retinal images acquired using fundus cameras are often visually blurred due to imperfect imaging conditions, refractive medium turbidity, and motion blur. In addition, ocular diseases such as the presence of cataract also result in blurred retinal images. The presence of blur in retinal fundus images reduces the effectiveness of the diagnosis process of an expert ophthalmologist or a computer-aided detection/diagnosis system. In this paper, we put forward a single-shot deep image prior (DIP)-based approach for retinal image enhancement. Unlike typical deep learning-based approaches, our method does not require any training data. Instead, our DIP-based method can learn the underlying image prior while using a single degraded image. To perform retinal image enhancement, we frame it as a layer decomposition problem and investigate the use of two well-known analytical priors, i.e., dark channel prior (DCP) and bright channel prior (BCP) for atmospheric light estimation. We show that both the untrained neural networks and the pretrained neural networks can be used to generate an enhanced image while using only a single degraded image. We evaluate our proposed framework quantitatively on five datasets using three widely used metrics and complement that with a subjective qualitative assessment of the enhancement by two expert ophthalmologists. We have compared our method with a recent state-of-the-art method cofe-Net using synthetically degraded retinal fundus images and show that our method outperforms the state-of-the-art method and provides a gain of 1.23 and 1.4 in average PSNR and SSIM respectively. Our method also outperforms other works proposed in the literature, which have evaluated their performance on non-public proprietary datasets, on the basis of the reported results.

show abstract

“…The output at the first iteration contains randomization due to random code vector z and the optimizer iteratively optimizes neural network's parameters θ for the given input image using backpropagation. It has been shown in the literature [19], [36] that the choice of neural network architectures has a direct impact on the performance, e.g., we can design/handcraft a particular neural network architecture for modeling a specific image [21]. This serves as a solution space when modeling images using untrained neural networks priors.…”

Section: Untrained and Pretrained Cdipsmentioning

confidence: 99%

Single-Shot Retinal Image Enhancement Using Untrained and Pretrained Neural Networks Priors Integrated with Analytical Image Priors

Qayyum¹,

Sultani²,

Shamshad³

et al. 2021

Preprint

1

0

View full text Add to dashboard Cite

Retinal images acquired using fundus cameras are often visually blurred due to imperfect imaging conditions, refractive medium turbidity, and motion blur. In addition, ocular diseases such as the presence of cataract also result in blurred retinal images. The presence of blur in retinal fundus images reduces the effectiveness of the diagnosis process of an expert ophthalmologist or a computer-aided detection/diagnosis system. In this paper, we put forward a single-shot deep image prior (DIP)-based approach for retinal image enhancement. Unlike typical deep learning-based approaches, our method does not require any training data. Instead, our DIP-based method can learn the underlying image prior while using a single degraded image. To perform retinal image enhancement, we frame it as a layer decomposition problem and investigate the use of two well-known analytical priors, i.e., dark channel prior (DCP) and bright channel prior (BCP) for atmospheric light estimation. We show that both the untrained neural networks and the pretrained neural networks can be used to generate an enhanced image while using only a single degraded image. We evaluate our proposed framework quantitatively on five datasets using three widely used metrics and complement that with a subjective qualitative assessment of the enhancement by two expert ophthalmologists. We have compared our method with a recent state-of-the-art method cofe-Net using synthetically degraded retinal fundus images and show that our method outperforms the state-of-the-art method and provides a gain of 1.23 and 1.4 in average PSNR and SSIM respectively. Our method also outperforms other works proposed in the literature, which have evaluated their performance on non-public proprietary datasets, on the basis of the reported results.

show abstract

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

Cited by 40 publications

References 69 publications

A Survey on Evolutionary Construction of Deep Neural Networks

A Survey on Evolutionary Construction of Deep Neural Networks

Single-Shot Retinal Image Enhancement Using Untrained and Pretrained Neural Networks Priors Integrated with Analytical Image Priors

Single-Shot Retinal Image Enhancement Using Untrained and Pretrained Neural Networks Priors Integrated with Analytical Image Priors

Contact Info

Product

Resources

About