# AdversarialNAS: Adversarial Neural Architecture Search for GANs

arXiv: https://arxiv.org/abs/1912.02037 · HTML: https://mlsanity.com/paper/1912.02037/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2019.

## Built on by (most cited first, 30 of 38)

- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Reformulating HOI Detection as Adaptive Set Prediction](https://mlsanity.com/paper/2103.05983/) (2021)
- [A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse](https://mlsanity.com/paper/2112.04660/) (2021)
- [Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation](https://mlsanity.com/paper/2105.06818/) (2021)
- [Styleformer: Transformer based Generative Adversarial Networks with Style Vector](https://mlsanity.com/paper/2106.07023/) (2021)
- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction](https://mlsanity.com/paper/2205.01608/) (2022)
- [WAS-VTON: Warping Architecture Search for Virtual Try-on Network](https://mlsanity.com/paper/2108.00386/) (2021)
- [AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression](https://mlsanity.com/paper/2105.12151/) (2021)
- [PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal](https://mlsanity.com/paper/2105.12324/) (2021)
- [Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2101.06658/) (2021)
- [Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis](https://mlsanity.com/paper/2207.05049/) (2022)
- [Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey](https://mlsanity.com/paper/2302.08641/) (2023)
- [RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving](https://mlsanity.com/paper/2108.08019/) (2021)
- [EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning](https://mlsanity.com/paper/2308.09915/) (2023)
- [EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs](https://mlsanity.com/paper/2111.15097/) (2021)
- [Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs](https://mlsanity.com/paper/2206.14658/) (2022)
- [Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search](https://mlsanity.com/paper/2304.05405/) (2023)
- [Towards Less Constrained Macro-Neural Architecture Search](https://mlsanity.com/paper/2203.05508/) (2022)
- [Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importance](https://mlsanity.com/paper/2303.16938/) (2023)
- [Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold](https://mlsanity.com/paper/2312.14776/) (2023)
- [MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery](https://mlsanity.com/paper/2402.18169/) (2024)
- [Learning High-Dimensional Distributions with Latent Neural Fokker-Planck Kernels](https://mlsanity.com/paper/2105.04538/) (2021)
- [Automating Generative Deep Learning for Artistic Purposes: Challenges and Opportunities](https://mlsanity.com/paper/2107.01858/) (2021)
- [Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search](https://mlsanity.com/paper/2307.15621/) (2023)
- [AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.13227/) (2021)
- [Neural Architecture Search: Two Constant Shared Weights Initialisations](https://mlsanity.com/paper/2302.04406/) (2023)

## Abstract (arXiv)

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 (1038). Experiments demonstrate the effectiveness and superiority of our method. The discovered generative model sets a new state-of-the-art FID score of 10.87 and highly competitive Inception Score of 8.74 on CIFAR-10. Its transferability is also proven by setting new state-of-the-art FID score of 26.98 and Inception score of 9.63 on STL-10. Code is at: urlhttps://github.com/chengaopro/AdversarialNAS.