No Modes Left Behind: Capturing the Data Distribution Effectively Using GANs

Authors: Shashank Sharma, Vinay Namboodiri

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

Reproducibility Variable Result LLM Response
Research Type Experimental We validate that the proposed method results in substantial improvements through its detailed analysis on toy and real datasets. The quantitative and qualitative results demonstrate that the proposed method improves the solution for the problem of missing modes and improves training of GANs.
Researcher Affiliation Academia Shashank Sharma, Vinay P. Namboodiri Dept. of Computer Science and Engineering Indian Institute of Technology, Kanpur
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the described methodology.
Open Datasets Yes We test our model extensively against natural images from popular datasets like Cifar10 (Krizhevsky 2009), Celeb A (Liu et al. 2015); and an unusual dataset, frames from a surveillance video, (Varadarajan and Odobez 2009).
Dataset Splits No The paper mentions using CIFAR 10, Celeb A, and a surveillance video dataset, but does not provide specific details on how these datasets were split into training, validation, and test sets (e.g., percentages or absolute counts).
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup No The paper states: 'We provide details regarding the network architectures and the parameter settings that we have used for the experiments in the supplementary material.' It does not provide these specific details in the main text.