Enhancing GAN Performance Through Neural Architecture Search and Tensor Decomposition

Pulakurthi, Prasanna Reddy; Mozaffari, Mahsa; Dianat, Sohail A.; Rabbani, Majid; Heard, Jamison; Rao, Raghuveer

doi:10.1109/icassp48485.2024.10446488

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Other1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Enhancing GANs With MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition

Reddy Pulakurthi,

Mozaffari,

Dianat

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Enhancing GANs With MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition

Reddy Pulakurthi,

Mozaffari,

Dianat

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Enhancing human action recognition with GAN-based data augmentation

Pulakurthi,

De Melo,

Rao

et al. 2024

Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) have emerged as a powerful tool for human action recognition, yet their reliance on vast amounts of high-quality labeled data poses significant challenges. A promising alternative is to train the network on generated synthetic data. However, existing synthetic data generation pipelines require complex simulation environments. Our novel solution bypasses this requirement by employing Generative Adversarial Networks (GANs) to generate synthetic data from only a small existing real-world dataset. Our training pipeline extracts the motion from each training video and augments it across various subject appearances within the training set. This approach increases the diversity in both motion and subject representations, thus significantly enhancing the model's performance. A rigorous evaluation of the model's performance is presented under diverse scenarios, including ground and aerial views. Moreover, an insightful analysis of critical factors influencing human action recognition performance, such as gesture motion diversity and subject appearance, is presented.

show abstract

Enhancing GAN Performance Through Neural Architecture Search and Tensor Decomposition

Cited by 2 publications

References 18 publications

Enhancing GANs With MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition

Enhancing GANs With MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition

Enhancing human action recognition with GAN-based data augmentation

Contact Info

Product

Resources

About