Sampling Strategies for GAN Synthetic Data
Cited 0 times inCited 0 times in
- Sampling Strategies for GAN Synthetic Data
- Bhattarai, Binod; Baek, Seungryul; Bodur, Rumeysa; Kim, Tae-Kyun
- Issue Date
- Institute of Electrical and Electronics Engineers Inc.
- IEEE International Conference on Acoustics, Speech and Signal Processing
- Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs). Studies have shown that the generated examples lack sufficient realism to train deep CNNs and are poor in diversity. Unlike previous studies of randomly augmenting the synthetic data with real data, we present our simple, effective and easy to implement synthetic data sampling methods to train deep CNNs more efficiently and accurately. To this end, we propose to maximally utilize the parameters learned during training of the GAN itself. These include discriminator's realism confidence score and the confidence on the target label of the synthetic data. In addition to this, we explore reinforcement learning (RL) to automatically search a subset of meaningful synthetic examples from a large pool of GAN synthetic data. We evaluate our method on two challenging face attribute classification data sets viz. AffectNet and CelebA. Our extensive experiments clearly demonstrate the need of sampling synthetic data before augmentation, which also improves the performance of one of the state-of-the-art deep CNNs in vitro.
- Appears in Collections:
- AI_Conference Papers
- Files in This Item:
- There are no files associated with this item.
can give you direct access to the published full text of this article. (UNISTARs only)
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.