GANFusion 结合 GAN 和扩散模型的优势，仅用单视图 2D 数据监督，先训练 GAN 生成 3D triplane 特征，再训练文本条件扩散模型从该特征空间采样，实现高保真的前馈文本到 3D 生成。
摘要：
我们仅使用单视图 2D 数据作为监督，训练了一个用于人类角色的前馈文本到 3D 扩散生成器。现有的 3D 生成模型尚无法匹配图像或视频生成模型的保真度。最先进的 3D 生成器要么使用显式 3D 监督进行训练，因此受限于现有 3D 数据的体积和多样性；要么仅使用 2D 数据作为监督进行训练，通常产生较粗糙的结果，无法以文本为条件，或必须诉诸测试时优化。我们观察到，基于 GAN 和扩散的生成器具有互补的特质：GAN 可以通过 2D 监督高效训练，生成高质量的 3D 对象，但难以以文本为条件。相反，去噪扩散模型可以高效地以文本为条件，但往往难以仅通过 2D 监督进行训练。我们提出了 GANFusion，它首先使用仅通过单视图 2D 数据训练的 GAN 架构，为 3D 数据生成无条件的 triplane 特征。然后，我们从 GAN 中生成随机样本，为它们添加标题，并训练一个以文本为条件的扩散模型，该模型直接学习从可被解码为 3D 对象的优质 triplane 特征空间中进行采样。
英文摘要：
We train a feed-forward text-to-3D diffusion generator for human characters using only single-view 2D data for supervision. Existing 3D generative models cannot yet match the fidelity of image or video generative models. State-of-the-art 3D generators are either trained with explicit 3D supervision and are thus limited by the volume and diversity of existing 3D data. Meanwhile, generators that can be trained with only 2D data as supervision typically produce coarser results, cannot be text-conditioned, or must revert to test-time optimization. We observe that GAN- and diffusion-based generators have complementary qualities: GANs can be trained efficiently with 2D supervision to produce high-quality 3D objects but are hard to condition on text. In contrast, denoising diffusion models can be conditioned efficiently but tend to be hard to train with only 2D supervision. We introduce GANFusion, which starts by generating unconditional triplane features for 3D data using a GAN architecture trained with only single-view 2D data. We then generate random samples from the GAN, caption them, and train a text-conditioned diffusion model that directly learns to sample from the space of good triplane features that can be decoded into 3D objects.
Generative Adversarial Networks (GANs) represent an attractive and novel approach to generate realistic data, such as genes, proteins, or drugs, in synthetic biology. Here, we apply GANs to generate synthetic DNA sequences encoding for proteins of variable length. We propose a novel feedback-loop architecture, called Feedback GAN (FBGAN), to optimize the synthetic gene sequences for desired properties using an external function analyzer. The proposed architecture also has the advantage that the analyzer need not be differentiable. We apply the feedback-loop mechanism to two examples: 1) genera…
Deep learning requires large datasets for training (convolutional) networks with millions of parameters. In neuroimaging, there are few open datasets with more than 100 subjects, which makes it difficult to, for example, train a classifier to discriminate controls from diseased persons. Generative adversarial networks (GANs) can be used to synthesize data, but virtually all research is focused on 2D images. In medical imaging, and especially in neuroimaging, most datasets are 3D or 4D. Here we therefore present preliminary results showing that a 3D progressive growing GAN can be used to synthe…
Augsburg University（奥格斯堡大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Friedrich-Alexander University Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
Job interviews are usually high-stakes social situations where professional and behavioral skills are required for a satisfactory outcome. Professional job interview trainers give educative feedback about the shown behavior according to common standards. This feedback can be helpful concerning the improvement of behavioral skills needed for job interviews. A technological approach for generating such feedback might be a playful and low-key starting point for job interview training. Therefore, we extended an interactive virtual job interview training system with a Generative Adversarial Network…
North Carolina State University（北卡罗来纳州立大学）；Pacific Northwest National Lab（太平洋西北国家实验室）；Texas A&M（德克萨斯农工大学）
This paper presents a novel, automated, generative adversarial networks (GAN) based synthetic feeder generation mechanism, abbreviated as FeederGAN. FeederGAN digests real feeder models represented by directed graphs via a deep learning framework powered by GAN and graph convolutional networks (GCN). Information of a distribution feeder circuit is extracted from its model input files so that the device connectivity is mapped onto the adjacency matrix and the device characteristics, such as circuit types (i.e., 3-phase, 2-phase, and 1-phase) and component attributes (e.g., length and current ra…
Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the dis- criminator from accessing global distributional statistics of generated samples, and often leads to mode dropping: the generator models only part of the target distribution. We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch. The latter score does not depend on …
Generative Adversarial Networks (GANs) are a revolutionary class of Deep Neural Networks (DNNs) that have been successfully used to generate realistic images, music, text, and other data. However, GAN training presents many challenges, notably it can be very resource-intensive. A potential weakness in GANs is that it requires a lot of data for successful training and data collection can be an expensive process. Typically, the corrective feedback from discriminator DNNs to generator DNNs (namely, the discriminator's assessment of the generated example) is calculated using only one real-numbered…
Advances in generative modeling based on GANs has motivated the community to find their use beyond image generation and editing tasks. In particular, several recent works have shown that GAN representations can be re-purposed for discriminative tasks such as part segmentation, especially when training data is limited. But how do these improvements stack-up against recent advances in self-supervised learning? Motivated by this we present an alternative approach based on contrastive learning and compare their performance on standard few-shot part segmentation benchmarks. Our experiments reveal t…
Interpreting CNN Predictions using Conditional Generative Adversarial Networks
Amrita Vishwa Vidyapeetham（阿米塔大学）；Universitat Politècnica de Catalunya (UPC-BarcelonaTECH)（加泰罗尼亚理工大学（巴塞罗那理工大学））；Institut de Recerca Sant Joan de Déu (IRSJD)（圣胡安·德·德乌研究所）
Air Force Research Laboratory（空军研究实验室）；Information Directorate（信息局）
Generative Adversarial Networks (GANs) have received a great deal of attention due in part to recent success in generating original, high-quality samples from visual domains. However, most current methods only allow for users to guide this image generation process through limited interactions. In this work we develop a novel GAN framework that allows humans to be "in-the-loop" of the image generation process. Our technique iteratively accepts relative constraints of the form "Generate an image more like image A than image B". After each constraint is given, the user is presented with new outpu…
Technion - Israel Institute of Technology（以色列理工学院）
Thanks to their remarkable generative capabilities, GANs have gained great popularity, and are used abundantly in state-of-the-art methods and applications. In a GAN based model, a discriminator is trained to learn the real data distribution. To date, it has been used only for training purposes, where it's utilized to train the generator to provide real-looking outputs. In this paper we propose a novel method that makes an explicit use of the discriminator in test-time, in a feedback manner in order to improve the generator results. To the best of our knowledge it is the first time a discrimin…
Xidian University（西安电子科技大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework. VHE randomized GAN (VHE-GAN) encodes an image to decode its associated text, and feeds the variational posterior as the source of randomness into the GAN image generator. We plug three off-the-shelf modules, including a deep topic model, a ladder-structured image encoder, and StackG…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Conditionality has become a core component for Generative Adversarial Networks (GANs) for generating synthetic images. GANs are usually using latent conditionality to control the generation process. However, tabular data only contains manifest variables. Thus, latent conditionality either restricts the generated data or does not produce sufficiently good results. Therefore, we propose a new methodology to include conditionality in tabular GANs inspired by image completion methods. This article presents ciDATGAN, an evolution of the Directed Acyclic Tabular GAN (DATGAN) that has already been sh…
This paper explores conditional image generation with a One-Vs-All classifier based on the Generative Adversarial Networks (GANs). Instead of the real/fake discriminator used in vanilla GANs, we propose to extend the discriminator to a One-Vs-All classifier (GAN-OVA) that can distinguish each input data to its category label. Specifically, we feed certain additional information as conditions to the generator and take the discriminator as a One-Vs-All classifier to identify each conditional category. Our model can be applied to different divergence or distances used to define the objective func…
We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator, but, instead, to satisfy a dynamic ensemble of discriminators. We show that this leads to a more generalized generator, promoting variety in the generated samples and avoiding the common mode collapse problem commonly experienced with generative adversarial networks (GANs). We f…
Latent Adversarial Regularization for Offline Preference Optimization
Department of Computer Science, Stanford University（斯坦福大学计算机科学系）；Siebel School of Computing（塞贝尔计算学院）；Data Science, University of Illinois at Urbana-Champaign（数据科学，伊利诺伊大学厄巴纳-香槟分校）
Shinshu University（信州大学）；University of Malaya（马来亚大学）
This paper proposes an extension to the Generative Adversarial Networks (GANs), namely as ARTGAN to synthetically generate more challenging and complex images such as artwork that have abstract characteristics. This is in contrast to most of the current solutions that focused on generating natural images such as room interiors, birds, flowers and faces. The key innovation of our work is to allow back-propagation of the loss function w.r.t. the labels (randomly assigned to each generated images) to the generator from the discriminator. With the feedback from the label information, the generator…
Robustness of deep learning models is a property that has recently gained increasing attention. We explore a notion of robustness for generative adversarial models that is pertinent to their internal interactive structure, and show that, perhaps surprisingly, the GAN in its original form is not robust. Our notion of robustness relies on a perturbed discriminator, or noisy, adversarial interference with its feedback. We explore, theoretically and empirically, the effect of model and training properties on this robustness. In particular, we show theoretical conditions for robustness that are sup…
Area of image inpainting over relatively large missing regions recently advanced substantially through adaptation of dedicated deep neural networks. However, current network solutions still introduce undesired artifacts and noise to the repaired regions. We present an image inpainting method that is based on the celebrated generative adversarial network (GAN) framework. The proposed PGGAN method includes a discriminator network that combines a global GAN (G-GAN) architecture with a patchGAN approach. PGGAN first shares network layers between G-GAN and patchGAN, then splits paths to produce two…
The Chinese University of Hong Kong（香港中文大学）；Xiaomi AI Lab（小米人工智能实验室）
Recent work has shown that a variety of semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to synthesize images. However, it is difficult to use these learned semantics for real image editing. A common practice of feeding a real image to a trained GAN generator is to invert it back to a latent code. However, existing inversion methods typically focus on reconstructing the target image by pixel values yet fail to land the inverted code in the semantic domain of the original latent space. As a result, the reconstructed image cannot well support sema…
Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new spee…
Brain vessel image segmentation can be used as a promising biomarker for better prevention and treatment of different diseases. One successful approach is to consider the segmentation as an image-to-image translation task and perform a conditional Generative Adversarial Network (cGAN) to learn a transformation between two distributions. In this paper, we present a novel multi-view approach, MLP-GAN, which splits a 3D volumetric brain vessel image into three different dimensional 2D images (i.e., sagittal, coronal, axial) and then feed them into three different 2D cGANs. The proposed MLP-GAN no…
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
Contemporary deep learning based inpainting algorithms are mainly based on a hybrid dual stage training policy of supervised reconstruction loss followed by an unsupervised adversarial critic loss. However, there is a dearth of literature for a fully unsupervised GAN based inpainting framework. The primary aversion towards the latter genre is due to its prohibitively slow iterative optimization requirement during inference to find a matching noise prior for a masked image. In this paper, we show that priors matter in GAN: we learn a data driven parametric network to predict a matching prior fo…
University of Toronto（多伦多大学）；University of Alberta（阿尔伯塔大学）
Computational histopathology image diagnosis becomes increasingly popular and important, where images are segmented or classified for disease diagnosis by computers. While pathologists do not struggle with color variations in slides, computational solutions usually suffer from this critical issue. To address the issue of color variations in histopathology images, this study proposes two stain style transfer models, SSIM-GAN and DSCSI-GAN, based on the generative adversarial networks. By cooperating structural preservation metrics and feedback of an auxiliary diagnosis net in learning, medical-…
End-to-end, autoregressive model-based TTS has shown significant performance improvements over the conventional one. However, the autoregressive module training is affected by the exposure bias, or the mismatch between the different distributions of real and predicted data. While real data is available in training, but in testing, only predicted data is available to feed the autoregressive module. By introducing both real and generated data sequences in training, we can alleviate the effects of the exposure bias. We propose to use Generative Adversarial Network (GAN) along with the key idea of…
National University of Singapore（新加坡国立大学）；University of California, Berkeley（加州大学伯克利分校）
Thermal comfort assessment for the built environment has become more available to analysts and researchers due to the proliferation of sensors and subjective feedback methods. These data can be used for modeling comfort behavior to support design and operations towards energy efficiency and well-being. By nature, occupant subjective feedback is imbalanced as indoor conditions are designed for comfort, and responses indicating otherwise are less common. This situation creates a scenario for the machine learning workflow where class balancing as a pre-processing step might be valuable for develo…
Future frame prediction in videos is a promising avenue for unsupervised video representation learning. Video frames are naturally generated by the inherent pixel flows from preceding frames based on the appearance and motion dynamics in the video. However, existing methods focus on directly hallucinating pixel values, resulting in blurry predictions. In this paper, we develop a dual motion Generative Adversarial Net (GAN) architecture, which learns to explicitly enforce future-frame predictions to be consistent with the pixel-wise flows in the video through a dual-learning mechanism. The prim…
OPPO US Research Center, InnoPeak Technology Inc（InnoPeak科技公司OPPO美国研究中心）；JD Finance America Corporation（京东金融美国公司）；University of Calgary（卡尔加里大学）；Ryerson University（瑞尔森大学）
The paper proposes a Dynamic ResBlock Generative Adversarial Network (DRB-GAN) for artistic style transfer. The style code is modeled as the shared parameters for Dynamic ResBlocks connecting both the style encoding network and the style transfer network. In the style encoding network, a style class-aware attention mechanism is used to attend the style feature representation for generating the style codes. In the style transfer network, multiple Dynamic ResBlocks are designed to integrate the style code and the extracted CNN semantic feature and then feed into the spatial window Layer-Instance…
Sabanci University（萨班哲大学）；University of Padua（帕多瓦大学）；Florida International University（佛罗里达国际大学）
In the past decades, the excessive use of the last-generation GAN (Generative Adversarial Networks) models in computer vision has enabled the creation of artificial face images that are visually indistinguishable from genuine ones. These images are particularly used in adversarial settings to create fake social media accounts and other fake online profiles. Such malicious activities can negatively impact the trustworthiness of users identities. On the other hand, the recent development of GAN models may create high-quality face images without evidence of spatial artifacts. Therefore, reassembl…
Human-Guided Shade Artifact Suppression in CBCT-to-MDCT Translation via Schrödinger Bridge with Conditional Diffusion
National Institute for Mathematical Sciences（国家信息科学研究院）；Department of Computer Engineering, Korea National University of Transportation（计算机工程系，韩国交通国立大学）
Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models are expressive and allow efficient computation of samples and derivatives, but cannot be used for computing likelihoods or for marginalization. The generative-adversarial training method allows to train such models through the use of an auxiliary discriminative neural network. We show that the generative-adversarial approach is a special case of an existing…
Peking University（北京大学）；Bytedance AI Lab（字节跳动人工智能实验室）
This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e.g., pose, head, upper clothes and pants) provided in various source inputs. The core idea of the proposed model is to embed human attributes into the latent space as independent codes and thus achieve flexible and continuous control of attributes via mixing and interpolation operations in explicit style representations. Specifically, a new architecture consisting of two encoding pathways with style block…
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and autoregressive models, such as WaveNet, remain the state of the art in generative modelling of audio signals such as human speech. To address this paucity, we introduce GAN-TTS, a Generative Adversarial Network for Text-to-Speech. Our architecture is composed of a conditional feed-forward generator producing raw speech audio, and an ensemble of discriminators whic…
Nanjing University（南京大学）；Politehnica University of Bucharest（布加勒斯特理工大学）；Leshan Normal University（乐山师范学院）；Henan Leyo Intelligent Technology Company（河南乐尧智能科技有限公司）
Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode collapse. To tackle these problems, we propose a novel mechanism. It first segments the entire sequence into several sub-sequences. Then these sub-sequences, together with the entire sequence, are evaluated individually by the discriminator. At last these feedback signals are all used to guide the learning of GAN. This mechanism learns the generation of both the e…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Calico Life Sciences（加利科生命科学）
In this work, we propose a composition/decomposition framework for adversarially training generative models on composed data - data where each sample can be thought of as being constructed from a fixed number of components. In our framework, samples are generated by sampling components from component generators and feeding these components to a composition function which combines them into a "composed sample". This compositional training approach improves the modularity, extensibility and interpretability of Generative Adversarial Networks (GANs) - providing a principled way to incrementally c…
Pseudo-random number generators (PRNG) are a fundamental element of many security algorithms. We introduce a novel approach to their implementation, by proposing the use of generative adversarial networks (GAN) to train a neural network to behave as a PRNG. Furthermore, we showcase a number of interesting modifications to the standard GAN architecture. The most significant is partially concealing the output of the GAN's generator, and training the adversary to discover a mapping from the overt part to the concealed part. The generator therefore learns to produce values the adversary cannot pre…
Shenzhen University（深圳大学）；Tencent AI Lab（腾讯人工智能实验室）
Training generative adversarial networks (GAN) in a distributed fashion is a promising technology since it is contributed to training GAN on a massive of data efficiently in real-world applications. However, GAN is known to be difficult to train by SGD-type methods (may fail to converge) and the distributed SGD-type methods may also suffer from massive amount of communication cost. In this paper, we propose a {distributed GANs training algorithm with quantized gradient, dubbed DQGAN,} which is the first distributed training method with quantized gradient for GANs. The new method trains GANs ba…
Norwegian University of Science and Technology（挪威科技大学）
While the whole world is still struggling with the COVID-19 pandemic, online learning and home office become more common. Many schools transfer their courses teaching to the online classroom. Therefore, it is significant to mine the students' feedback and opinions from their reviews towards studies so that both schools and teachers can know where they need to improve. This paper trains machine learning and deep learning models using both balanced and imbalanced datasets for sentiment classification. Two SOTA category-aware text generation GAN models: CatGAN and SentiGAN, are utilized to synthe…
Recently, GAN vocoders have seen rapid progress in speech synthesis, starting to outperform autoregressive models in perceptual quality with much higher generation speed. However, autoregressive vocoders are still the common choice for neural generation of speech signals coded at very low bit rates. In this paper, we present a GAN vocoder which is able to generate wideband speech waveforms from parameters coded at 1.6 kbit/s. The proposed model is a modified version of the StyleMelGAN vocoder that can run in frame-by-frame manner, making it suitable for streaming applications. The experimental…
State-of-the-art offline handwriting text recognition systems tend to use neural networks and therefore require a large amount of annotated data to be trained. In order to partially satisfy this requirement, we propose a system based on Generative Adversarial Networks (GAN) to produce synthetic images of handwritten words. We use bidirectional LSTM recurrent layers to get an embedding of the word to be rendered, and we feed it to the generator network. We also modify the standard GAN by adding an auxiliary network for text recognition. The system is then trained with a balanced combination of …
NASA Langley Research Center（美国国家航空航天局兰利研究中心）；University of Puerto Rico (Mayagüez)（波多黎各大学（马亚圭斯））
While standard generative adversarial networks (GANs) rely solely on training data to learn unknown probability distributions, physics-informed GANs (PI-GANs) encode physical laws in the form of stochastic partial differential equations (PDEs) using auto differentiation. By relating observed data to unobserved quantities of interest through PDEs, PI-GANs allow for the estimation of underlying probability distributions without their direct measurement (i.e. inverse problems). The scalable nature of GANs allows high-dimensional, spatially-dependent probability distributions (i.e., random fields)…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）
We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise model is known or not. When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN). The main idea is to corrupt the label of the generated sample before feeding to the adversarial discriminator, forcing the generator …
Comparative clinical evaluation of "memory-efficient" synthetic 3d generative adversarial networks (gan) head-to-head to state of art: results on computed tomography of the chest
Politecnico di Milano（米兰理工大学）；Fondazione IRCCS Policlinico San Matteo Pavia（圣马泰奥基金会IRCCS帕维亚医院）；Università degli studi di Pavia（帕维亚大学）；IULM University（IULM大学）
Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image. Since these models are trained on a single image, they are limited in their scale and application. To overcome these issues, we propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. In the presented meta-learning approach, a single-image GAN model is generated given an input image, via a convolutional feedforward hypernetwork $f$. This network is t…
Yandex；Moscow Institute of Physics and Technology（莫斯科物理技术学院）
StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing existing images requires embedding a given image into the latent space of StyleGAN2. Latent code optimization via backpropagation is commonly used for qualitative embedding of real world images, although it is prohibitively slow for many applications. We propose a way to distill a particular image manipulation of StyleGAN2 into image-to-image network trained in pai…
DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation
University of Science and Technology of China（中国科学技术大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
针对多阶段文生图中静态文本语义指导不足的问题，本文提出 DSE-GAN，通过 DSE 模块依据历史图文反馈动态重组语义，并结合 SAMA 架构提升生成质量。
