DeepAI AI Chat
Log In Sign Up

Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample

by   Itamar Winter, et al.
Hebrew University of Jerusalem

The generation of synthetic images is currently being dominated by Generative Adversarial Networks (GANs). Despite their outstanding success in generating realistic looking images, they still suffer from major drawbacks, including an unstable and highly sensitive training procedure, mode-collapse and mode-mixture, and dependency on large training sets. In this work we present a novel non-adversarial generative method - Clustered Optimization of LAtent space (COLA), which overcomes some of the limitations of GANs, and outperforms GANs when training data is scarce. In the full data regime, our method is capable of generating diverse multi-class images with no supervision, surpassing previous non-adversarial methods in terms of image quality and diversity. In the small-data regime, where only a small sample of labeled images is available for training with no access to additional unlabeled data, our results surpass state-of-the-art GAN models trained on the same amount of data. Finally, when utilizing our model to augment small datasets, we surpass the state-of-the-art performance in small-sample classification tasks on challenging datasets, including CIFAR-10, CIFAR-100, STL-10 and Tiny-ImageNet. A theoretical analysis supporting the essence of the method is presented.


page 1

page 4

page 7

page 8

page 13

page 16

page 17


Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors

Unconditional image generation has recently been dominated by generative...

Escaping from Collapsing Modes in a Constrained Space

Generative adversarial networks (GANs) often suffer from unpredictable m...

Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks

Designing a logo for a new brand is a lengthy and tedious back-and-forth...

Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms

Climate change is increasing the frequency and severity of harmful algal...

Improving sample diversity of a pre-trained, class-conditional GAN by changing its class embeddings

Mode collapse is a well-known issue with Generative Adversarial Networks...

Investigating the Potential of Auxiliary-Classifier GANs for Image Classification in Low Data Regimes

Generative Adversarial Networks (GANs) have shown promise in augmenting ...

Instance Selection for GANs

Recent advances in Generative Adversarial Networks (GANs) have led to th...