Activation Maximization Generative Adversarial Nets

Authors: Zhiming Zhou, Han Cai, Shu Rong, Yuxuan Song, Kan Ren, Weinan Zhang, Jun Wang, Yong Yu

ICLR 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments have been conducted to validate our analysis and evaluate the effectiveness of our solution, where AM-GAN outperforms other strong baselines and achieves state-of-the-art Inception Score (8.91) on CIFAR-10.
Researcher Affiliation Collaboration Zhiming Zhou, Han Cai Shanghai Jiao Tong University heyohai,hcai@apex.sjtu.edu.cn Shu Rong Yitu Tech shu.rong@yitu-inc.com Yuxuan Song, Kan Ren Shanghai Jiao Tong University songyuxuan,kren@apex.sjtu.edu.cn Jun Wang University College London j.wang@cs.ucl.ac.uk Weinan Zhang, Yu Yong Shanghai Jiao Tong University wnzhang@sjtu.edu.cn, yyu@apex.sjtu.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes The repeatable experiment code is published for further research3. 3Link for anonymous experiment code: https://github.com/ZhimingZhou/AM-GAN
Open Datasets Yes We conduct experiments on the image benchmark datasets including CIFAR-10 and Tiny-Image Net2 which comprises 200 classes with 500 training images per class. 2https://tiny-imagenet.herokuapp.com/
Dataset Splits No The paper mentions using CIFAR-10 and Tiny-Image Net datasets but does not explicitly provide details about specific training/validation/test splits, such as percentages or sample counts for each partition.
Hardware Specification No The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers, such as library or solver names and their exact versions.
Experiment Setup Yes Optimizer: Adam with beta1=0.5, beta2=0.999; Batch size=100. Learning rate: Exponential decay with stair, initial learning rate 0.0004. We use weight normalization for each weight