We propose a new architecture and training methodology for generative adversarial networks. Current approaches attempt to learn the transformation from a noise sample to a generated data sample in one shot. Our proposed generator architecture, called $\textit{ChainGAN}$, uses a two-step process. It first attempts to transform a noise vector into a crude sample, similar to a traditional generator. Next, a chain of networks, called $\textit{editors}$, attempt to sequentially enhance this sample. We train each of these units independently, instead of with end-to-end backpropagation on the entire chain. Our model is robust, efficient, and flexible as we can apply it to various network architectures. We provide rationale for our choices and experimentally evaluate our model, achieving competitive results on several datasets.
Haverford College（哈弗福德学院）；University of Pennsylvania（宾夕法尼亚大学）
Generative Adversarial Networks (GANs) have been shown to aid in the creation of artificial data in situations where large amounts of real data are difficult to come by. This issue is especially salient in the computational linguistics space, where researchers are often tasked with modeling the complex morphologic and grammatical processes of low-resource languages. This paper will discuss the implementation and testing of a GAN that attempts to model and reproduce the graphotactics of a language using only 100 example strings. These artificial, yet graphotactically compliant, strings are mean…
Southern University of Science and Technology（南方科技大学）
Search-based procedural content generation methods have recently been introduced for the autonomous creation of bullet hell games. Search-based methods, however, can hardly model patterns of danmakus -- the bullet hell shooting entity -- explicitly and the resulting levels often look non-realistic. In this paper, we present a novel bullet hell game platform named Keiki, which allows the representation of danmakus as a parametric sequence which, in turn, can model the sequential behaviours of danmakus. We employ three types of generative adversarial networks (GANs) and test Keiki across three m…
University of Twente（屯特大学）；University of Amsterdam（阿姆斯特丹大学）
The visual world we sense, interpret and interact everyday is a complex composition of interleaved physical entities. Therefore, it is a very challenging task to generate vivid scenes of similar complexity using computers. In this work, we present a scene generation framework based on Generative Adversarial Networks (GANs) to sequentially compose a scene, breaking down the underlying problem into smaller ones. Different than the existing approaches, our framework offers an explicit control over the elements of a scene through separate background and foreground generators. Starting with an init…
Converting text descriptions into images using Generative Adversarial Networks has become a popular research area. Visually appealing images have been generated successfully in recent years. Inspired by these studies, we investigated the generation of artistic images on a large variance dataset. This dataset includes images with variations, for example, in shape, color, and content. These variations in images provide originality which is an important factor for artistic essence. One major characteristic of our work is that we used keywords as image descriptions, instead of sentences. As the ne…
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
Previous works on sequential learning address the problem of forgetting in discriminative models. In this paper we consider the case of generative models. In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion. We first show that sequential fine tuning renders the network unable to properly generate images from previous categories (i.e. forgetting). Addressing this problem, we propose Memory Replay GANs (MeRGANs), a conditional GAN framework that integrates a memory replay generator. We study two methods to prevent fo…
Microsoft Research（微软研究院）；Aalto University（阿尔托大学）；YaiYai Ltd（YaiYai有限公司）
This work offers a novel theoretical perspective on why, despite numerous attempts, adversarial approaches to generative modeling (e.g., GANs) have not been as popular for certain generation tasks, particularly sequential tasks such as Natural Language Generation, as they have in others, such as Computer Vision. In particular, on sequential data such as text, maximum-likelihood approaches are significantly more utilized than GANs. We show that, while it may seem that maximizing likelihood is inherently different than minimizing distinguishability, this distinction is largely artificial and onl…
University of Applied Sciences（应用科学大学）；Information Technologies Institute（信息技术研究所）
Sequential data in industrial applications can be used to train and evaluate machine learning models (e.g. classifiers). Since gathering representative amounts of data is difficult and time consuming, there is an incentive to generate it from a small ground truth. Data augmentation is a common method to generate more data through a priori knowledge with one specific method, so called generative adversarial networks (GANs), enabling data generation from noise. This paper investigates the possibility of using GANs in order to augment sequential Internet of Things (IoT) data, with an example impl…
University of California, Los Angeles（加州大学洛杉矶分校）；Google Brain（谷歌大脑）
GANs involve training two networks in an adversarial game, where each network's task depends on its adversary. Recently, several works have framed GAN training as an online or continual learning problem. We focus on the discriminator, which must perform classification under an (adversarially) shifting data distribution. When trained on sequential tasks, neural networks exhibit \emph{forgetting}. For GANs, discriminator forgetting leads to training instability. To counter forgetting, we encourage the discriminator to maintain useful representations by adding a self-supervision. Conditional GANs…
Toyota Technological Institute（丰田工业大学）；Toyota Motor Corporation（丰田汽车公司）；Osaka University（大阪大学）
Generative Adversarial Networks (GANs) have shown remarkable successes in generating realistic images and interpolating changes between images. Existing models, however, do not take into account physical contexts behind images in generating the images, which may cause unrealistic changes. Furthermore, it is difficult to generate the changes at a specific timing and they often do not match with actual changes. This paper proposes a novel GAN, named Physical Context and Timing aware sequence generating GANs (PCTGAN), that generates an image in a sequence at a specific timing between two images w…
Generative adversarial networks (GANs) represent a zero-sum game between two machine players, a generator and a discriminator, designed to learn the distribution of data. While GANs have achieved state-of-the-art performance in several benchmark learning tasks, GAN minimax optimization still poses great theoretical and empirical challenges. GANs trained using first-order optimization methods commonly fail to converge to a stable solution where the players cannot improve their objective, i.e., the Nash equilibrium of the underlying game. Such issues raise the question of the existence of Nash e…
Memorial University of Newfoundland（纽芬兰纪念大学）；University of Waterloo（滑铁卢大学）
In this paper we present a method for algorithmic melody generation using a generative adversarial network without recurrent components. Music generation has been successfully done using recurrent neural networks, where the model learns sequence information that can help create authentic sounding melodies. Here, we use DC-GAN architecture with dilated convolutions and towers to capture sequential information as spatial image information, and learn long-range dependencies in fixed-length melody forms such as Irish traditional reel.
University of California at Riverside（加州大学河滨分校）；Emory University（埃默里大学）；Riverside Community Hospital（河滨社区医院）
While deep learning approaches have shown remarkable performance in many imaging tasks, most of these methods rely on availability of large quantities of data. Medical image data, however, is scarce and fragmented. Generative Adversarial Networks (GANs) have recently been very effective in handling such datasets by generating more data. If the datasets are very small, however, GANs cannot learn the data distribution properly, resulting in less diverse or low-quality results. One such limited dataset is that for the concurrent gain of 19 and 20 chromosomes (19/20 co-gain), a mutation with posit…
We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Network (GAN) architecture that utilizes Spatial Transformer Networks (STNs) as the generator, which we call Spatial Transformer GANs (ST-GANs). ST-GANs seek image realism by operating in the geometric warp parameter space. In particular, we exploit an iterative STN warping scheme and propose a sequential training strategy that achieves better results compared to naive training o…
University of Hamburg（汉堡大学）；Adobe Research（Adobe研究院）
Recently there has been an interest in the potential of learning generative models from a single image, as opposed to from a large dataset. This task is of practical significance, as it means that generative models can be used in domains where collecting a large dataset is not feasible. However, training a model capable of generating realistic images from only a single sample is a difficult problem. In this work, we conduct a number of experiments to understand the challenges of training these methods and propose some best practices that we found allowed us to generate improved results over pr…
Existing methods of level generation using latent variable models such as VAEs and GANs do so in segments and produce the final level by stitching these separately generated segments together. In this paper, we build on these methods by training VAEs to learn a sequential model of segment generation such that generated segments logically follow from prior segments. By further combining the VAE with a classifier that determines whether to place the generated segment to the top, bottom, left or right of the previous segment, we obtain a pipeline that enables the generation of arbitrarily long le…
The University of Sydney（悉尼大学）；University of New South Wales（新南威尔士大学）；University of Pittsburgh（匹兹堡大学）；Microsoft Corporation（微软公司）
Image-to-image translation is significant to many computer vision and machine learning tasks such as image synthesis and video synthesis. It has primary applications in the graphics editing and animation industries. With the development of generative adversarial networks, a lot of attention has been drawn to image-to-image translation tasks. In this paper, we propose and investigate a novel task named as panoptic-level image-to-image translation and a naive baseline of solving this task. Panoptic-level image translation extends the current image translation task to two separate objectives of s…
The difficulty in obtaining labeled data relevant to a given task is among the most common and well-known practical obstacles to applying deep learning techniques to new or even slightly modified domains. The data volumes required by the current generation of supervised learning algorithms typically far exceed what a human needs to learn and complete a given task. We investigate ways to expand a given labeled corpus of remote sensed imagery into a larger corpus using Generative Adversarial Networks (GANs). We then measure how these additional synthetic data affect supervised machine learning p…
In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversarial networks (GANs) are introduced to penalize the unrealistic generated samples. To exploit the supervision signal from the discriminator, most previous models leverage REINFORCE to address the non-differentiable problem of sequential discrete data. However, because of the unstable property of the training signal during the dynamic process of adversarial training, the effectiveness of REINFORCE, in this case, is hard…
Popular generative model learning methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple distributions such as isotropic Gaussian. In this paper, we argue that learning a complicated distribution over the latent space of an auto-encoder enables more accurate modeling of complicated data distributions. Based on this observation, we propose a two stage optimization procedure which maximizes an approximate implicit density model. We experimentally verify that our method outperforms GANs and VAEs on two image da…
Generative adversarial networks (GANs) have proven hugely successful in variety of applications of image processing. However, generative adversarial networks for handwriting is relatively rare somehow because of difficulty of handling sequential handwriting data by Convolutional Neural Network (CNN). In this paper, we propose a handwriting generative adversarial network framework (HWGANs) for synthesizing handwritten stroke data. The main features of the new framework include: (i) A discriminator consists of an integrated CNN-Long-Short-Term- Memory (LSTM) based feature extraction with Path Si…
Center for Research in Computer Vision, University of Central Florida（中佛罗里达大学计算机视觉研究中心）
Learning to generate natural scenes has always been a challenging task in computer vision. It is even more painstaking when the generation is conditioned on images with drastically different views. This is mainly because understanding, corresponding, and transforming appearance and semantic information across the views is not trivial. In this paper, we attempt to solve the novel problem of cross-view image synthesis, aerial to street-view and vice versa, using conditional generative adversarial networks (cGAN). Two new architectures called Crossview Fork (X-Fork) and Crossview Sequential (X-Se…
In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). However, standard Autoencoders (AEs) and closely related structures have remained popular because they are easy to train and adapt to different tasks. An interesting question is if we can achieve state-of-the-art performance with AEs while retaining their good properties. We propose an answer to this question by introducing a new model called Y-Autoencoder (Y-AE). The structure and training procedure…
Even though Generative Adversarial Networks (GANs) have shown a remarkable ability to generate high-quality images, GANs do not always guarantee the generation of photorealistic images. Occasionally, they generate images that have defective or unnatural objects, which are referred to as 'artifacts'. Research to investigate why these artifacts emerge and how they can be detected and removed has yet to be sufficiently carried out. To analyze this, we first hypothesize that rarely activated neurons and frequently activated neurons have different purposes and responsibilities for the progress of g…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Ulsan National Institute of Science and Technology (UNIST)（蔚山国立科学技术院）；INEEJI
Generative Adversarial Networks (GANs) have shown satisfactory performance in synthetic image generation by devising complex network structure and adversarial training scheme. Even though GANs are able to synthesize realistic images, there exists a number of generated images with defective visual patterns which are known as artifacts. While most of the recent work tries to fix artifact generations by perturbing latent code, few investigate internal units of a generator to fix them. In this work, we devise a method that automatically identifies the internal units generating various types of art…
Recommender systems are an essential part of any e-commerce platform. Recommendations are typically generated by aggregating large amounts of user data. A malicious actor may be motivated to sway the output of such recommender systems by injecting malicious datapoints to leverage the system for financial gain. In this work, we propose a semi-supervised attack detection algorithm to identify the malicious datapoints. We do this by leveraging a portion of the dataset that has a lower chance of being polluted to learn the distribution of genuine datapoints. Our proposed approach modifies the Gene…
Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several machine translation and summarization benchmarks. These benchmarks are often defined by validation perplexity even though this is not a direct measure of the quality of the generated text. Additionally, these models are typically trained via maxi- mum likelihood and teacher forcing. These methods are well-suited to optimizing perplexity but can result in poor sam…
Research Center for Information Technology Innovation, Academia Sinica（中央研究院信息技术创新研究中心）；Department of Computer Science, National Tsing Hua University（国立清华大学计算机科学系）
Generating music has a few notable differences from generating images and videos. First, music is an art of time, necessitating a temporal model. Second, music is usually composed of multiple instruments/tracks with their own temporal dynamics, but collectively they unfold over time interdependently. Lastly, musical notes are often grouped into chords, arpeggios or melodies in polyphonic music, and thereby introducing a chronological ordering of notes is not naturally suitable. In this paper, we propose three models for symbolic multi-track music generation under the framework of generative ad…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Pohang University of Science and Technology (POSTECH)（浦项科技大学）；AItrics
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). However, previous methods often fail in challenging cases, in particular, when an image has multiple target instances and a translation task involves significant changes in shape, e.g., translating pants to skirts in fashion images. To tackle the issues, we propose a novel method, coined instance-aware GAN (InstaGAN), that incorporates the instance information (e.g., object segmentation masks) and improves multi-instance transfiguratio…
IBM T.J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
We present a deep learning model for data-driven simulations of random dynamical systems without a distributional assumption. The deep learning model consists of a recurrent neural network, which aims to learn the time marching structure, and a generative adversarial network (GAN) to learn and sample from the probability distribution of the random dynamical system. Although GANs provide a powerful tool to model a complex probability distribution, the training often fails without a proper regularization. Here, we propose a regularization strategy for a GAN based on consistency conditions for th…
Predictive process monitoring aims to predict future characteristics of an ongoing process case, such as case outcome or remaining timestamp. Recently, several predictive process monitoring methods based on deep learning such as Long Short-Term Memory or Convolutional Neural Network have been proposed to address the problem of next event prediction. However, due to insufficient training data or sub-optimal network configuration and architecture, these approaches do not generalize well the problem at hand. This paper proposes a novel adversarial training framework to address this shortcoming, b…
Imperial College London（帝国理工学院）；University of Exeter（埃克塞特大学）；Foundation for Research and Technology - Hellas (FORTH)（希腊研究与技术基金会）
Facial video re-targeting is a challenging problem aiming to modify the facial attributes of a target subject in a seamless manner by a driving monocular sequence. We leverage the 3D geometry of faces and Generative Adversarial Networks (GANs) to design a novel deep learning architecture for the task of facial and head reenactment. Our method is different to purely 3D model-based approaches, or recent image-based methods that use Deep Convolutional Neural Networks (DCNNs) to generate individual frames. We manage to capture the complex non-rigid facial motion from the driving monocular performa…
Wide applications of differentiable two-player sequential games (e.g., image generation by GANs) have raised much interest and attention of researchers to study efficient and fast algorithms. Most of the existing algorithms are developed based on nice properties of simultaneous games, i.e., convex-concave payoff functions, but are not applicable in solving sequential games with different settings. Some conventional gradient descent ascent algorithms theoretically and numerically fail to find the local Nash equilibrium of the simultaneous game or the local minimax (i.e., local Stackelberg equil…
Courant Institute of Mathematical Sciences, New York University（纽约大学柯朗数学科学研究所）；Element AI（Element AI公司）；Center for Data Science, New York University（纽约大学数据科学中心）；Facebook AI Research, Facebook Inc.（Facebook公司Facebook人工智能研究院）
This article proposes Adversarially-Trained Normalized Noisy-Feature Auto-Encoder (ATNNFAE) for byte-level text generation. An ATNNFAE consists of an auto-encoder where the internal code is normalized on the unit sphere and corrupted by additive noise. Simultaneously, a replica of the decoder (sharing the same parameters as the AE decoder) is used as the generator and fed with random latent vectors. An adversarial discriminator is trained to distinguish training samples reconstructed from the AE from samples produced through the random-input generator, making the entire generator-discriminator…
