The recent explosive interest on transformers has suggested their potential to become powerful "universal" models for computer vision tasks, such as classification, detection, and segmentation. While those attempts mainly study the discriminative models, we explore transformers on some more notoriously difficult vision tasks, e.g., generative adversarial networks (GANs). Our goal is to conduct the first pilot study in building a GAN completely free of convolutions, using only pure transformer-based architectures. Our vanilla GAN architecture, dubbed TransGAN, consists of a memory-friendly transformer-based generator that progressively increases feature resolution, and correspondingly a multi-scale discriminator to capture simultaneously semantic contexts and low-level textures. On top of them, we introduce the new module of grid self-attention for alleviating the memory bottleneck further, in order to scale up TransGAN to high-resolution generation. We also develop a unique training recipe including a series of techniques that can mitigate the training instability issues of TransGAN, such as data augmentation, modified normalization, and relative position encoding. Our best architecture achieves highly competitive performance compared to current state-of-the-art GANs using convolutional backbones. Specifically, TransGAN sets new state-of-the-art inception score of 10.43 and FID of 18.28 on STL-10, outperforming StyleGAN-V2. When it comes to higher-resolution (e.g. 256 x 256) generation tasks, such as on CelebA-HQ and LSUN-Church, TransGAN continues to produce diverse visual examples with high fidelity and impressive texture details. In addition, we dive deep into the transformer-based generation models to understand how their behaviors differ from convolutional ones, by visualizing training dynamics. The code is available at https://github.com/VITA-Group/TransGAN.
Fraunhofer ITWM（弗劳恩霍夫工业数学研究所）；University of Heidelberg（海德堡大学）；Fraunhofer Center Machine Learning（弗劳恩霍夫机器学习中心）；Technical University of Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Offenburg University（奥芬堡大学）
Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed with convolutional neural networks. At the same time, image synthesis using generative adversarial networks (GANs) has drastically improved over the last few years. The recently proposed TransGAN is the first GAN using only transformer-based architectures and achieves competitive results when compared to convolutional GANs. However, since transformers are data-hungry architectures, TransGAN requires data augmentation, a…
GANs can generate photo-realistic images from the domain of their training data. However, those wanting to use them for creative purposes often want to generate imagery from a truly novel domain, a task which GANs are inherently unable to do. It is also desirable to have a level of control so that there is a degree of artistic direction rather than purely curation of random results. Here we present a method for interpolating between generative models of the StyleGAN architecture in a resolution dependent manner. This allows us to generate images from an entirely novel domain and do this with a…
Center for Research in Computer Vision (CRCV), University of Central Florida（中佛罗里达大学计算机视觉研究中心（CRCV））
We address the problem of generating images across two drastically different views, namely ground (street) and aerial (overhead) views. Image synthesis by itself is a very challenging computer vision task and is even more so when generation is conditioned on an image in another view. Due the difference in viewpoints, there is small overlapping field of view and little common content between these two views. Here, we try to preserve the pixel information between the views so that the generated image is a realistic representation of cross view input image. For this, we propose to use homography …
a Division of Medical Informatics, Department of Biomedical Engineering, Link\" o ping University, Link\" o ping, Sweden b Division of Statistics；Machine Learning, Department of Computer；Information Science, Link\" o ping University, Link\" o ping, Sweden c Center for Medical Image Science；Visualization (CMIV), Link\" o ping University, Link\" o ping, Sweden
In medical imaging, a general problem is that it is costly and time consuming to collect high quality data from healthy and diseased subjects. Generative adversarial networks (GANs) is a deep learning method that has been developed for synthesizing data. GANs can thereby be used to generate more realistic training data, to improve classification performance of machine learning algorithms. Another application of GANs is image-to-image translations, e.g. generating magnetic resonance (MR) images from computed tomography (CT) images, which can be used to obtain multimodal datasets from a single m…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Despite the tantalizing success in a broad of vision tasks, transformers have not yet demonstrated on-par ability as ConvNets in high-resolution image generative modeling. In this paper, we seek to explore using pure transformers to build a generative adversarial network for high-resolution image synthesis. To this end, we believe that local attention is crucial to strike the balance between computational efficiency and modeling capacity. Hence, the proposed generator adopts Swin transformer in a style-based architecture. To achieve a larger receptive field, we propose double attention which s…
Zhejiang Normal University（浙江师范大学）；Huzhou University（湖州师范学院）；Zhejiang University（浙江大学）；Hangzhou Dianzi University（杭州电子科技大学）
One-shot image generation (OSG) with generative adversarial networks that learn from the internal patches of a given image has attracted world wide attention. In recent studies, scholars have primarily focused on extracting features of images from probabilistically distributed inputs with pure convolutional neural networks (CNNs). However, it is quite difficult for CNNs with limited receptive domain to extract and maintain the global structural information. Therefore, in this paper, we propose a novel structure-preserved method TcGAN with individual vision transformer to overcome the shortcomi…
Despite the extensive studies on Generative Adversarial Networks (GANs), how to reliably sample high-quality images from their latent spaces remains an under-explored topic. In this paper, we propose a novel GAN latent sampling method by exploring and exploiting the hubness priors of GAN latent distributions. Our key insight is that the high dimensionality of the GAN latent space will inevitably lead to the emergence of hub latents that usually have much larger sampling densities than other latents in the latent space. As a result, these hub latents are better trained and thus contribute more …
University of Bologna（博洛尼亚大学）；Google Inc.（谷歌公司）；Technische Universität München（慕尼黑工业大学）
Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at relaxing these assumptions enabling training of conditional generative models for novel view synthesis in a completely unsupervised manner. We first pre-train a purely generative decoder model using a 3D-aware GAN formulation while at the same time train an encoder network to invert the mapping from latent space to images. Then, we swap encoder and decoder and t…
A very recent trend in generative modeling is building 3D-aware generators from 2D image collections. To induce the 3D bias, such models typically rely on volumetric rendering, which is expensive to employ at high resolutions. During the past months, there appeared more than 10 works that address this scaling issue by training a separate 2D decoder to upsample a low-resolution image (or a feature tensor) produced from a pure 3D generator. But this solution comes at a cost: not only does it break multi-view consistency (i.e. shape and texture change when the camera moves), but it also learns th…
National Technical University of Athens（雅典国立技术大学）；Google Brain（谷歌大脑）；UT Austin（德克萨斯大学奥斯汀分校）
We introduce a new local sparse attention layer that preserves two-dimensional geometry and locality. We show that by just replacing the dense attention layer of SAGAN with our construction, we obtain very significant FID, Inception score and pure visual improvements. FID score is improved from $18.65$ to $15.94$ on ImageNet, keeping all other parameters the same. The sparse attention patterns that we propose for our new layer are designed using a novel information theoretic criterion that uses information flow graphs. We also present a novel way to invert Generative Adversarial Networks with …
Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics
International Institute of Information Technology, Bangalore（国际信息技术学院（班加罗尔））；Ulster University（阿尔斯特大学）；Dr B R Ambedkar National Institute of Technology Jalandhar（阿姆倍伽尔博士国家技术学院贾朗达尔分校）
We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images. This is not easily possible with existing INN models due to some fundamental limitations. The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning image into maximally informative features. All parameters of a cINN are jointly optimized with a stable, maximum likelihood-based training procedure. Even though INN-based models have received…
Diffusion models have achieved unprecedented performance in generative modeling. The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually denoised samples, as opposed to the simpler (e.g., Gaussian) latent space of GANs, VAEs, and normalizing flows. This paper provides an alternative, Gaussian formulation of the latent space of various diffusion models, as well as an invertible DPM-Encoder that maps images into the latent space. While our formulation is purely based on the definition of diffusion models, we demonstrate several intriguing consequences. …
Improving the Effectiveness of Deep Generative Data
Bosch Center for Artificial Intelligence（博世人工智能中心）；Institute of Industrial Manufacturing and Management IFF, University of Stuttgart（斯图加特大学工业制造与管理研究所）；Fraunhofer Institute for Manufacturing Engineering and Automation (IPA)（弗劳恩霍夫制造工程与自动化研究所）
We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models to conditional image generation and performs super-resolution through a stochastic denoising process. Inference starts with pure Gaussian noise and iteratively refines the noisy output using a U-Net model trained on denoising at various noise levels. SR3 exhibits strong performance on super-resolution tasks at different magnification factors, on faces and natural images. We conduct human evaluation on a standard 8X face super-resolution task on CelebA-HQ, comparing…
Zhejiang University（浙江大学）；JD Explore Academy（京东探索研究院）；Tencent AI Lab（腾讯人工智能实验室）；Tencent Data Platform（腾讯数据平台部）；Microsoft（微软）
Generative Adversarial Networks (GANs) are formulated as minimax game problems, whereby generators attempt to approach real data distributions by virtue of adversarial learning against discriminators. The intrinsic problem complexity poses the challenge to enhance the performance of generative networks. In this work, we aim to boost model learning from the perspective of network architectures, by incorporating recent progress on automated architecture search into GANs. To this end, we propose a fully differentiable search framework for generative adversarial networks, dubbed alphaGAN. The sear…
