paper-with-me

홈 › Papers

Neural Architecture Search for Deep Image Prior

2020-01-14 · Kary Ho, Andrew Gilbert, Hailin Jin, John Collomosse

We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed Deep Image Prior (DIP). We show that evolutionary search can automatically optimize the encoder-decoder (E-D) structure and meta-parameters of the DIP network, which serves as a content-specific prior to regularize these single image restoration tasks. Our binary representation encodes the design space for an asymmetric E-D network that typically converges to yield a content-specific DIP within 10-20 generations using a population size of 500. The optimized architectures consistently improve upon the visual quality of classical DIP for a diverse range of photographic and artistic content.

📄 PDF Abstract BibTeX arXiv:2001.04776

Code (2)

Pol22/NAS_DIP tf
wackygerbs/NAS-DIP

Tasks

DecoderImage RestorationNeural Architecture SearchSuper-Resolution

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

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

2020-08-26 · ECCV 2020 8 · Yun-Chun Chen, Chen Gao, Esther Robb, Jia-Bin Huang

Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior for solving various inverse image restoration tasks. Instead of using hand-designed architectures, we…

Image RestorationImage-to-Image TranslationNeural Architecture SearchTranslation

Multi-Prior Learning via Neural Architecture Search for Blind Face Restoration

2022-06-28 · Yanjiang Yu, Puyang Zhang, Kaihao Zhang, Wenhan Luo 외

Blind Face Restoration (BFR) aims to recover high-quality face images from low-quality ones and usually resorts to facial priors for improving restoration performance. However, current methods still suffer from two major…

Blind Face RestorationNeural Architecture Search

ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior

2021-11-27 · CVPR 2022 1 · Metin Ersin Arican, Ozgur Kara, Gustav Bredell, Ender Konukoglu

Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework…

DenoisingImage DenoisingImage RestorationInductive Bias+2

Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement

2020-12-10 · CVPR 2021 1 · Risheng Liu, Long Ma, Jiaao Zhang, Xin Fan 외

Low-light image enhancement plays very important roles in low-level vision field. Recent works have built a large variety of deep learning models to address this task. However, these approaches mostly rely on significant…

Image EnhancementLow-Light Image EnhancementRolling Shutter Correction

GI-NAS: Boosting Gradient Inversion Attacks through Adaptive Neural Architecture Search

2024-05-31 · Wenbo Yu, Hao Fang, Bin Chen, Xiaohang Sui 외

Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients and have raised considerable privacy concerns. A majority of gradient inve…

Federated LearningNeural Architecture Search