On the Effects of Batch and Weight Normalization in Generative Adversarial Networks
Sitao Xiang and Hao Li
arXiv e-Print archive - 2017 via Local arXiv
Keywords: stat.ML, cs.CV, cs.LG
First published: 2017/04/13 (8 years ago)
Abstract: Generative adversarial networks (GANs) are highly effective unsupervised learning frameworks that can generate very sharp data, even for data such as images with complex, highly multimodal distributions. However GANs are known to be very hard to train, suffering from problems such as mode collapse and disturbing visual artifacts. Batch normalization (BN) techniques have been introduced to address the training problem. However, though BN accelerates training in the beginning, our experiments show that the use of BN can be unstable and negatively impact the quality of the trained model. The evaluation of BN and numerous other recent schemes for improving GAN training is hindered by the lack of an effective objective quality measure for GAN models. To address these issues, we first introduce a weight normalization (WN) approach for GAN training that significantly improves the stability, efficiency and the quality of the generated samples. To allow a methodical evaluation, we introduce a new objective measure based on a squared Euclidean reconstruction error metric, to assess training performance in terms of speed, stability, and quality of generated samples. Our experiments indicate that training using WN is generally superior to BN for GANs. We provide statistical evidence for commonly used datasets (CelebA, LSUN, and CIFAR-10), that WN achieves 10% lower mean squared loss for reconstruction and significantly better qualitative results than BN.
more
less
Sitao Xiang and Hao Li
arXiv e-Print archive - 2017 via Local arXiv
Keywords: stat.ML, cs.CV, cs.LG
First published: 2017/04/13 (8 years ago)
Abstract: Generative adversarial networks (GANs) are highly effective unsupervised learning frameworks that can generate very sharp data, even for data such as images with complex, highly multimodal distributions. However GANs are known to be very hard to train, suffering from problems such as mode collapse and disturbing visual artifacts. Batch normalization (BN) techniques have been introduced to address the training problem. However, though BN accelerates training in the beginning, our experiments show that the use of BN can be unstable and negatively impact the quality of the trained model. The evaluation of BN and numerous other recent schemes for improving GAN training is hindered by the lack of an effective objective quality measure for GAN models. To address these issues, we first introduce a weight normalization (WN) approach for GAN training that significantly improves the stability, efficiency and the quality of the generated samples. To allow a methodical evaluation, we introduce a new objective measure based on a squared Euclidean reconstruction error metric, to assess training performance in terms of speed, stability, and quality of generated samples. Our experiments indicate that training using WN is generally superior to BN for GANs. We provide statistical evidence for commonly used datasets (CelebA, LSUN, and CIFAR-10), that WN achieves 10% lower mean squared loss for reconstruction and significantly better qualitative results than BN.
[link]
* They analyze the effects of using Batch Normalization (BN) and Weight Normalization (WN) in GANs (classical algorithm, like DCGAN).
* They introduce a new measure to rate the quality of the generated images over time.
### How
* They use BN as it is usually defined.
* They use WN with the following formulas:
* Strict weight-normalized layer:
* 
* Affine weight-normalized layer:
* 
* As activation units they use Translated ReLUs (aka "threshold functions"):
* 
* `alpha` is a learned parameter.
* TReLUs play better with their WN layers than normal ReLUs.
* Reconstruction measure
* To evaluate the quality of the generated images during training, they introduce a new measure.
* The measure is based on a L2-Norm (MSE) between (1) a real image and (2) an image created by the generator that is as similar as possible to the real image.
* They generate (2) by starting `G(z)` with a noise vector `z` that is filled with zeros. The desired output is the real image. They compute a MSE between the generated and real image and backpropagate the result. Then they use the generated gradient to update `z`, while leaving the parameters of `G` unaltered. They repeat this for a defined number of steps.
* Note that the above described method is fairly time-consuming, so they don't do it often.
* Networks
* Their networks are fairly standard.
* Generator: Starts at 1024 filters, goes down to 64 (then 3 for the output). Upsampling via fractionally strided convs.
* Discriminator: Starts at 64 filters, goes to 1024 (then 1 for the output). Downsampling via strided convolutions.
* They test three variations of these networks:
* Vanilla: No normalization. PReLUs in both G and D.
* BN: BN in G and D, but not in the last layers and not in the first layer of D. PReLUs in both G and D.
* WN: Strict weight-normalized layers in G and D, except for the last layers, which are affine weight-normalized layers. TPReLUs (Translated PReLUs) in both G and D.
* Other
* They train with RMSProp and batch size 32.
### Results
* Their WN formulation trains stable, provided the learning rate is set to 0.0002 or lower.
* They argue, that their achieved stability is similar to the one in WGAN.
* BN had significant swings in quality.
* Vanilla collapsed sooner or later.
* Both BN and Vanilla reached an optimal point shortly after the start of the training. After that, the quality of the generated images only worsened.
* Plot of their quality measure:
* 
* Their quality measure is based on reconstruction of input images. The below image shows examples for that reconstruction (each person: original image, vanilla reconstruction, BN rec., WN rec.).
* 
* Examples generated by their WN network:
* 
How
Results
Your comment:
|
You must log in before you can submit this summary! Your draft will not be saved!
Preview:
