Low-Rank Subspaces in GANs

Authors: Jiapeng Zhu, Ruili Feng, Yujun Shen, Deli Zhao, Zheng-Jun Zha, Jingren Zhou, Qifeng Chen

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on state-of-the-art GAN models (including Style GAN2 and Big GAN) trained on various datasets demonstrate the effectiveness of our Low Rank GAN.
Researcher Affiliation Collaboration Jiapeng Zhu1 Ruili Feng2,3 Yujun Shen4 Deli Zhao2 Zheng-Jun Zha3 Jingren Zhou2 Qifeng Chen1 1Hong Kong University of Science and Technology 2Alibaba Group 3University of Science and Technology of China 4Byte Dance Inc.
Pseudocode No The paper describes mathematical formulations and processes, but it does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes Code is available at https://github.com/zhujiapeng/Low Rank GAN/.
Open Datasets Yes The datasets we use are diverse, including FFHQ [18], LSUN [36] and Image Net [9].
Dataset Splits No The paper mentions using datasets for experiments but does not provide specific details on how the data was split into training, validation, and test sets (e.g., percentages or sample counts for each split).
Hardware Specification No The paper does not specify the hardware used for running experiments (e.g., specific GPU or CPU models, memory, or cloud instance types).
Software Dependencies No The paper mentions models like StyleGAN2 and BigGAN, and segmentation models like [20] and Pixel Lib, but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes Note that in the experiments of car and church, for the small mask regions, a relatively larger rrelax is needed. Here we set rrelax = 20.