AdversarialNAS: Adversarial Neural Architecture Search for GANs
arXiv:1912.02037
Abstract
Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields. In this paper, we propose an AdversarialNAS method specially tailored for Generative Adversarial Networks (GANs) to search for a superior generative model on the task of unconditional image generation. The AdversarialNAS is the first method that can search the architectures of generator and discriminator simultaneously in a differentiable manner. During searching, the designed adversarial search algorithm does not need to comput any extra metric to evaluate the performance of the searched architecture, and the search paradigm considers the relevance between the two network architectures and improves their mutual balance. Therefore, AdversarialNAS is very efficient and only takes 1 GPU day to search for a superior generative model in the proposed large search space (). Experiments demonstrate the effectiveness and superiority of our method. The discovered generative model sets a new state-of-the-art FID score of and highly competitive Inception Score of on CIFAR-10. Its transferability is also proven by setting new state-of-the-art FID score of and Inception score of on STL-10. Code is at: \url{https://github.com/chengaopro/AdversarialNAS}.
arXiv commentAccepted to CVPR 2020
References in corpus (23)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Neural Architecture Search with Reinforcement Learning
- Spectral Normalization for Generative Adversarial Networks
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- NICE: Non-linear Independent Components Estimation
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
- SNAS: Stochastic Neural Architecture Search
- Random Search and Reproducibility for Neural Architecture Search
- One-Shot Neural Architecture Search via Self-Evaluated Template Network
- LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
- Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
- Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
- Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
- AGAN: Towards Automated Design of Generative Adversarial Networks
- Class-Splitting Generative Adversarial Networks
- Efficient Differentiable Neural Architecture Search with Meta Kernels
- PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
- UGAN: Untraceable GAN for Multi-Domain Face Translation
- Highly Efficient Salient Object Detection with 100K Parameters
- Customizable Architecture Search for Semantic Segmentation