One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to incorporate into existing implementations. We tested the efficacy of spectral normalization on CIFAR10, STL-10, and ILSVRC2012 dataset, and we experimentally confirmed that spectrally normalized GANs (SN-GANs) is capable of generating images of better or equal quality relative to the previous training stabilization techniques.

/pdf/spectral-normalization-for-generative-adversarial-networks-3dxutlj1bi.pdf

Spectral Normalization for Generative Adversarial Networks

Visual signals in a video can be divided into content and motion. While content specifies which objects are in the video, motion describes their dynamics. Based on this prior, we propose the Motion and Content decomposed Generative Adversarial Network (MoCoGAN) framework for video generation. The proposed framework generates a video by mapping a sequence of random vectors to a sequence of video frames. Each random vector consists of a content part and a motion part. While the content part is kept fixed, the motion part is realized as a stochastic process. To learn motion and content decomposition in an unsupervised manner, we introduce a novel adversarial learning scheme utilizing both image and video discriminators. Extensive experimental results on several challenging datasets with qualitative and quantitative comparison to the state-of-the-art approaches, verify effectiveness of the proposed framework. In addition, we show that MoCoGAN allows one to generate videos with same content but different motion as well as videos with different content and same motion. Our code is available at https://github.com/sergeytulyakov/mocogan.

/pdf/mocogan-decomposing-motion-and-content-for-video-generation-17uppx4uyl.pdf

MoCoGAN: Decomposing Motion and Content for Video Generation

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the schema and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used datasets for images, videos, audios, and 3D data, as well as the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning.

Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the main components and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used image and video datasets and the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning.

Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey

In this paper, we propose a generative model, Temporal Generative Adversarial Nets (TGAN), which can learn a semantic representation of unlabeled videos, and is capable of generating videos. Unlike existing Generative Adversarial Nets (GAN)-based methods that generate videos with a single generator consisting of 3D deconvolutional layers, our model exploits two different types of generators: a temporal generator and an image generator. The temporal generator takes a single latent variable as input and outputs a set of latent variables, each of which corresponds to an image frame in a video. The image generator transforms a set of such latent variables into a video. To deal with instability in training of GAN with such advanced networks, we adopt a recently proposed model, Wasserstein GAN, and propose a novel method to train it stably in an end-to-end manner. The experimental results demonstrate the effectiveness of our methods.

Temporal Generative Adversarial Nets with Singular Value Clipping

Training of generative adversarial network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation. In general, the computational cost of training GAN scales exponentially with the resolution. In this study, we present a novel memory efficient method of unsupervised learning of high-resolution video dataset whose computational cost scales only linearly with the resolution. We achieve this by designing the generator model as a stack of small sub-generators and training the model in a specific way. We train each sub-generator with its own specific discriminator. At the time of the training, we introduce between each pair of consecutive sub-generators an auxiliary subsampling layer that reduces the frame-rate by a certain ratio. This procedure can allow each sub-generator to learn the distribution of the video at different levels of resolution. We also need only a few GPUs to train a highly complex generator that far outperforms the predecessor in terms of inception scores.

Train Sparsely, Generate Densely: Memory-Efficient Unsupervised Training of High-Resolution Temporal GAN

Despite significant progress of deep learning in the field of computer vision, there has not been a software library that covers these methods in a unifying manner. We introduce ChainerCV, a software library that is intended to fill this gap. ChainerCV supports numerous neural network models as well as software components needed to conduct research in computer vision. These implementations emphasize simplicity, flexibility and good software engineering practices. The library is designed to perform on par with the results reported in published papers and its tools can be used as a baseline for future research in computer vision. Our implementation includes sophisticated models like Faster R-CNN and SSD, and covers tasks such as object detection and semantic segmentation.

ChainerCV: a Library for Deep Learning in Computer Vision

Referring to existing illustrations helps novice drawers to realize their ideas. To find such helpful references from a large image collection, we first build a semantic vector representation of illustrations by training convolutional neural networks. As the proposed vector space correctly reflects the semantic meanings of illustrations, users can efficiently search for references with similar attributes. Besides the search with a single query, a semantic morphing algorithm that searches the intermediate illustrations that gradually connect two queries is proposed. Several experiments were conducted to demonstrate the effectiveness of our methods.

Illustration2Vec: a semantic vector representation of illustrations

In this paper, we propose a novel method to efficiently train a Generative Adversarial Network (GAN) on high dimensional samples. The key idea is to introduce a differentiable subsampling layer which appropriately reduces the dimensionality of intermediate feature maps in the generator during training. In general, generators require large memory and computational costs in the latter stages of the network as the feature maps become larger, though the latter stages have relatively fewer parameters than the earlier stages. It makes training large models for video generation difficult due to the limited computational resource. We solve this problem by introducing a method that gradually reduces the dimensionality of feature maps in the generator with multiple subsampling layers. We also propose a network (Temporal GAN v2) with such layers and perform video generation experiments. As a consequence, our model trained on the UCF101 dataset at $192 \times 192$ pixels achieves an Inception Score (IS) of 24.34, which shows a significant improvement over the previous state-of-the-art score of 14.56.

Masaki Saito

Papers

Temporal Generative Adversarial Nets with Singular Value Clipping

Train Sparsely, Generate Densely: Memory-Efficient Unsupervised Training of High-Resolution Temporal GAN

ChainerCV: a Library for Deep Learning in Computer Vision

Illustration2Vec: a semantic vector representation of illustrations

TGANv2: Efficient Training of Large Models for Video Generation with Multiple Subsampling Layers