Influence Estimation for Generative Adversarial Networks

Authors: Naoyuki Terashita, Hiroki Ohashi, Yuichi Nonaka, Takashi Kanemaru

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We experimentally verified that our influence estimation method correctly inferred the changes in GAN evaluation metrics. We also demonstrated that the removal of the identified harmful instances effectively improved the model s generative performance with respect to various GAN evaluation metrics.
Researcher Affiliation Industry Naoyuki Terashita Hiroki Ohashi Yuichi Nonaka Takashi Kanemaru Hitachi, Ltd. Tokyo, Japan
Pseudocode Yes Algorithm 1 Training Phase and Algorithm 2 Inference Phase
Open Source Code Yes Code is at https://github.com/hitachi-rd-cv/influence-estimation-for-gans
Open Datasets Yes DCGAN (Radford et al., 2016) trained with MNIST (Le Cun et al., 1998)
Dataset Splits No The paper mentions training and test datasets but does not explicitly provide details about a validation dataset split, its size, or how it was used for hyperparameter tuning during training.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types) used to run its experiments.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup Yes Table 2: Hyper parameters in Section 5.1. and Table 5: Hyper parameters in Section 5.2.