Jiaze Sun

Jiaze Sun, Binod Bhattarai, Zhixiang Chen et al.

Semantically guided conditional Generative Adversarial Networks (cGANs) have become a popular approach for face editing in recent years. However, most existing methods introduce semantic masks as direct conditional inputs to the generator and often require the target masks to perform the corresponding translation in the RGB space. We propose SeCGAN, a novel label-guided cGAN for editing face images utilising semantic information without the need to specify target semantic masks. During training, SeCGAN has two branches of generators and discriminators operating in parallel, with one trained to translate RGB images and the other for semantic masks. To bridge the two branches in a mutually beneficial manner, we introduce a semantic consistency loss which constrains both branches to have consistent semantic outputs. Whilst both branches are required during training, the RGB branch is our primary network and the semantic branch is not needed for inference. Our results on CelebA and CelebA-HQ demonstrate that our approach is able to generate facial images with more accurate attributes, outperforming competitive baselines in terms of Target Attribute Recognition Rate whilst maintaining quality metrics such as self-supervised Fréchet Inception Distance and Inception Score.

Jiaze Sun, Binod Bhattarai, Tae-Kyun Kim

We present a novel self-supervised learning approach for conditional generative adversarial networks (GANs) under a semi-supervised setting. Unlike prior self-supervised approaches which often involve geometric augmentations on the image space such as predicting rotation angles, our pretext task leverages the label space. We perform augmentation by randomly sampling sensible labels from the label space of the few labelled examples available and assigning them as target labels to the abundant unlabelled examples from the same distribution as that of the labelled ones. The images are then translated and grouped into positive and negative pairs by their target labels, acting as training examples for our pretext task which involves optimising an auxiliary match loss on the discriminator's side. We tested our method on two challenging benchmarks, CelebA and RaFD, and evaluated the results using standard metrics including Fréchet Inception Distance, Inception Score, and Attribute Classification Rate. Extensive empirical evaluation demonstrates the effectiveness of our proposed method over competitive baselines and existing arts. In particular, our method surpasses the baseline with only 20% of the labelled examples used to train the baseline.

Jian-Feng Cai, Dong Li, Jiaze Sun et al.

Random projections are able to perform dimension reduction efficiently for datasets with nonlinear low-dimensional structures. One well-known example is that random matrices embed sparse vectors into a low-dimensional subspace nearly isometrically, known as the restricted isometric property in compressed sensing. In this paper, we explore some applications of random projections in deep neural networks. We provide the expressive power of fully connected neural networks when the input data are sparse vectors or form a low-dimensional smooth manifold. We prove that the number of neurons required for approximating a Lipschitz function with a prescribed precision depends on the sparsity or the dimension of the manifold and weakly on the dimension of the input vector. The key in our proof is that random projections embed stably the set of sparse vectors or a low-dimensional smooth manifold into a low-dimensional subspace. Based on this fact, we also propose some new neural network models, where at each layer the input is first projected onto a low-dimensional subspace by a random projection and then the standard linear connection and non-linear activation are applied. In this way, the number of parameters in neural networks is significantly reduced, and therefore the training of neural networks can be accelerated without too much performance loss.