ExprGAN: Facial Expression Editing With Controllable Expression Intensity

Authors: Hui Ding, Kumar Sricharan, Rama Chellappa

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

Reproducibility Variable Result LLM Response
Research Type Experimental Quantitative and qualitative evaluations on the widely used Oulu-CASIA dataset demonstrate the effectiveness of Expr GAN.
Researcher Affiliation Collaboration Hui Ding,1 Kumar Sricharan,2 Rama Chellappa3 1,3University of Maryland, College Park 2PARC, Palo Alto
Pseudocode No The paper describes algorithms and training steps in paragraph form, but does not include any clearly labeled "Pseudocode" or "Algorithm" blocks or figures.
Open Source Code No The paper does not explicitly state that source code for the described methodology is publicly available, nor does it provide a link to a code repository.
Open Datasets Yes We evaluated the proposed Expr GAN on the widely used Oulu-CASIA (Zhao et al. 2011) dataset.
Dataset Splits Yes Training and testing sets are divided based on identity, with 1296 for training and 144 for testing.
Hardware Specification No The paper does not specify the hardware used for training or experimentation, such as specific GPU or CPU models. It only mentions the use of Tensorflow.
Software Dependencies No The paper mentions "Tensorflow (Abadi et al. 2016)" but does not specify its version number or any other software dependencies with version numbers, such as programming languages or libraries.
Experiment Setup Yes We train the networks using the Adam optimizer (Kingma and Ba 2014), with learning rate of 0.0002, β1 = 0.5, β2 = 0.999 and mini-batch size of 48. In the image refining stage, we empirically set λ1 = 1, λ2 = 1, λ3 = 0.01, λ4 = 0.01, λ5 = 0.001.