TY - JOUR AU - Jeon, Insu AU - Lee, Wonkwang AU - Pyeon, Myeongjang AU - Kim, Gunhee PY - 2021/05/18 Y2 - 2024/03/28 TI - IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 9 SE - AAAI Technical Track on Machine Learning II DO - 10.1609/aaai.v35i9.16967 UR - https://ojs.aaai.org/index.php/AAAI/article/view/16967 SP - 7926-7934 AB - We propose a new GAN-based unsupervised model for disentangled representation learning. The new model is discovered in an attempt to utilize the Information Bottleneck (IB) framework to the optimization of GAN, thereby named IB-GAN. The architecture of IB-GAN is partially similar to that of InfoGAN but has a critical difference; an intermediate layer of the generator is leveraged to constrain the mutual information between the input and the generated output. The intermediate stochastic layer can serve as a learnable latent distribution that is trained with the generator jointly in an end-to-end fashion. As a result, the generator of IB-GAN can harness the latent space in a disentangled and interpretable manner. With the experiments on dSprites and Color-dSprites dataset, we demonstrate that IB-GAN achieves competitive disentanglement scores to those of state-of-the-art β-VAEs and outperforms InfoGAN. Moreover, the visual quality and the diversity of samples generated by IB-GAN are often better than those by β-VAEs and Info-GAN in terms of FID score on CelebA and 3D Chairs dataset. ER -