We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a paired image-to-image translation task, using noise-to-image pairs of the diffusion model's ODE trajectory. For efficient regression loss computation, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space, utilizing an ensemble of augmentations. Furthermore, we adapt a diffusion model to construct a multi-scale discriminator with a text alignment loss to build an effective conditional GAN-based formulation. E-LatentLPIPS converges more efficiently than many existing distillation methods, even accounting for dataset construction costs. We demonstrate that our one-step generator outperforms cutting-edge one-step diffusion distillation models -- DMD, SDXL-Turbo, and SDXL-Lightning -- on the zero-shot COCO benchmark.
Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）
Generative Adversarial Networks (GANs) have become a powerful approach for generative image modeling. However, GANs are notorious for their training instability, especially on large-scale, complex datasets. While the recent work of BigGAN has significantly improved the quality of image generation on ImageNet, it requires a huge model, making it hard to deploy on resource-constrained devices. To reduce the model size, we propose a black-box knowledge distillation framework for compressing GANs, which highlights a stable and efficient training process. Given BigGAN as the teacher network, we man…
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices. In contrast to traditional instance-level distillation, we design a novel GAN compression oriented knowledge by slicing the contents of teacher outputs into multiple fine-grained granularities, such as row/column strips (global information) and image patches (local information), modeling the relationships among them, such as pairwise distance and triplet-wise angle, and encouraging the student to capture these rela…
Generative Adversarial Networks (GANs) are an arrange of two neural networks -- the generator and the discriminator -- that are jointly trained to generate artificial data, such as images, from random inputs. The quality of these generated images has recently reached such levels that can often lead both machines and humans into mistaking fake for real examples. However, the process performed by the generator of the GAN has some limitations when we want to condition the network to generate images from subcategories of a specific class. Some recent approaches tackle this \textit{conditional gene…
Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process. Conditional GANs (cGANs) provide a mechanism to control the generation process by conditioning the output on a user defined input. Although training GANs requires only unsupervised data, training cGANs requires labelled data which can be very expensive to obtain. We propose a framework for semi-supervised training of cGANs which utilizes sparse labels to learn the …
In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains. The controllable synthesis ability of GAN generators suggests that they maintain informative, disentangled, and explainable image representations, but leveraging and transferring their representations to downstream tasks is largely unexplored. In this paper, we propose to distill knowledge from GAN generators by squeezing and spanning their representations. We squeeze the generator features into representations that are …
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…
Recently, subsampling or refining images generated from unconditional GANs has been actively studied to improve the overall image quality. Unfortunately, these methods are often observed less effective or inefficient in handling conditional GANs (cGANs) -- conditioning on a class (aka class-conditional GANs) or a continuous variable (aka continuous cGANs or CcGANs). In this work, we introduce an effective and efficient subsampling scheme, named conditional density ratio-guided rejection sampling (cDR-RS), to sample high-quality images from cGANs. Specifically, we first develop a novel conditio…
Bosch Center for Artificial Intelligence（博世人工智能中心）
This paper introduces a novel and fully unsupervised framework for conditional GAN training in which labels are automatically obtained from data. We incorporate a clustering network into the standard conditional GAN framework that plays against the discriminator. With the generator, it aims to find a shared structured mapping for associating pseudo-labels with the real and fake images. Our generator outperforms unconditional GANs in terms of FID with significant margins on large scale datasets like ImageNet and LSUN. It also outperforms class conditional GANs trained on human labels on CIFAR10…
We propose a simple but effective modification of the discriminators, namely measure-conditional discriminators, as a plug-and-play module for different GANs. By taking the generated distributions as part of input so that the target optimum for the discriminator is stationary, the proposed discriminator is more robust than the vanilla one. A variant of the measure-conditional discriminator can also handle multiple target distributions, or act as a surrogate model of statistical distances such as KL divergence with applications to transfer learning.
Invasive ductal carcinoma (IDC) comprises nearly 80% of all breast cancers. The detection of IDC is a necessary preprocessing step in determining the aggressiveness of the cancer, determining treatment protocols, and predicting patient outcomes, and is usually performed manually by an expert pathologist. Here, we describe a novel algorithm for automatically detecting IDC using semi-supervised conditional generative adversarial networks (cGANs). The framework is simple and effective at improving scores on a range of metrics over a baseline CNN.
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）
Conditional generative models aim to learn the underlying joint distribution of data and labels to achieve conditional data generation. Among them, the auxiliary classifier generative adversarial network (AC-GAN) has been widely used, but suffers from the problem of low intra-class diversity of the generated samples. The fundamental reason pointed out in this paper is that the classifier of AC-GAN is generator-agnostic, which therefore cannot provide informative guidance for the generator to approach the joint distribution, resulting in a minimization of the conditional entropy that decreases …
Yandex（扬德克斯）；National Research University Higher School of Economics（国立研究型大学高等经济学院）
Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable likelihoods and allow for stable training. However, they have to be carefully designed to represent invertible functions with efficient Jacobian determinant calculation. In practice, these requirements lead to overparameterized and sophisticated architectures that are inferior to alternative feed-forward models in terms of inference time and memory consumption. In t…
In recent years, unsupervised/weakly-supervised conditional generative adversarial networks (GANs) have achieved many successes on the task of modeling and generating data. However, one of their weaknesses lies in their poor ability to separate, or disentangle, the different factors that characterize the representation encoded in their latent space. To address this issue, we propose a novel structure for unsupervised conditional GANs powered by a novel Information Compensation Connection (IC-Connection). The proposed IC-Connection enables GANs to compensate for information loss incurred during…
GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study of transfer learning of these models is therefore an urgent topic. Many of the available high-quality pretrained GANs are unconditional (like StyleGAN). For many applications, however, conditional GANs are preferable, because they provide more control over the generation process, despite often suffering more training difficulties. Therefore, in this paper, we focus on transferri…
We examined the use of modern Generative Adversarial Nets to generate novel images of oil paintings using the Painter By Numbers dataset. We implemented Spectral Normalization GAN (SN-GAN) and Spectral Normalization GAN with Gradient Penalty, and compared their outputs to a Deep Convolutional GAN. Visually, and quantitatively according to the Sliced Wasserstein Distance metric, we determined that the SN-GAN produced paintings that were most comparable to our training dataset. We then performed a series of experiments to add supervised conditioning to SN-GAN, the culmination of which is what we…
Maxwell Institute for Mathematical Sciences（麦克斯韦数学科学研究所）
We consider the filtering and prediction problem for a diffusion process. The signal and observation are modeled by stochastic differential equations (SDEs) driven by correlated Wiener processes. In classical estimation theory, measure-valued stochastic partial differential equations (SPDEs) are derived for the filtering and prediction measures. These equations can be hard to solve numerically. We provide an approximation algorithm using conditional generative adversarial networks (GANs) in combination with signatures, an object from rough path theory. The signature of a sufficiently smooth pa…
Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks. We introduce a simple yet effective approach to improving cGANs by measuring the discrepancy between the data distribution and the model distribution on given samples. The proposed measure, coined the gap of log-densities (GOLD), provides an effective self-diagnosis for cGANs while being efficienty computed from the discriminator. We propose three applications of the GOLD: example re-weighting, rejectio…
In this paper, we have developed a general-purpose architecture, Vit-Gan, capable of performing most of the image-to-image translation tasks from semantic image segmentation to single image depth perception. This paper is a follow-up paper, an extension of generator-based model [1] in which the obtained results were very promising. This opened the possibility of further improvements with adversarial architecture. We used a unique vision transformers-based generator architecture and Conditional GANs(cGANs) with a Markovian Discriminator (PatchGAN) (https://github.com/YigitGunduc/vit-gan). In th…
Generative Adversarial Networks (GANs) are a well-known technique that is trained on samples (e.g. pictures of fruits) and which after training is able to generate realistic new samples. Conditional GANs (CGANs) additionally provide label information for subclasses (e.g. apple, orange, pear) which enables the GAN to learn more easily and increase the quality of its output samples. We use GANs to learn architectural features of major cities and to generate images of buildings which do not exist. We show that currently available GAN and CGAN architectures are unsuited for this task and propose a…
Understanding the mechanism of generative adversarial networks (GANs) helps us better use GANs for downstream applications. Existing efforts mainly target interpreting unconditional models, leaving it less explored how a conditional GAN learns to render images regarding various categories. This work fills in this gap by investigating how a class conditional generator unifies the synthesis of multiple classes. For this purpose, we dive into the widely used class-conditional batch normalization (CCBN), and observe that each feature channel is activated at varying degrees given different categori…
Conditional GANs are widely used in translating an image from one category to another. Meaningful conditions to GANs provide greater flexibility and control over the nature of the target domain synthetic data. Existing conditional GANs commonly encode target domain label information as hard-coded categorical vectors in the form of 0s and 1s. The major drawbacks of such representations are inability to encode the high-order semantic information of target categories and their relative dependencies. We propose a novel end-to-end learning framework with Graph Convolutional Networks to learn the at…
Bernoulli Institute, University of Groningen（格罗宁根大学伯努利研究所）
The task of text-to-image generation has achieved remarkable progress due to the advances in the conditional generative adversarial networks (GANs). However, existing conditional text-to-image GANs approaches mostly concentrate on improving both image quality and semantic relevance but ignore the explainability of the model which plays a vital role in real-world applications. In this paper, we present a variety of techniques to take a deep look into the latent space and semantic space of the conditional text-to-image GANs model. We introduce pairwise linear interpolation of latent codes and `l…
Renault Software Factory（雷诺软件工厂）；CNRS-I3S, Université Côte d’Azur（法国国家科学研究中心-I3S，蔚蓝海岸大学）
This paper proposes two important contributions for conditional Generative Adversarial Networks (cGANs) to improve the wide variety of applications that exploit this architecture. The first main contribution is an analysis of cGANs to show that they are not explicitly conditional. In particular, it will be shown that the discriminator and subsequently the cGAN does not automatically learn the conditionality between inputs. The second contribution is a new method, called a contrario cGAN, that explicitly models conditionality for both parts of the adversarial architecture via a novel a contrari…
Existing approaches and datasets for face aging produce results skewed towards the mean, with individual variations and expression wrinkles often invisible or overlooked in favor of global patterns such as the fattening of the face. Moreover, they offer little to no control over the way the faces are aged and can difficultly be scaled to large images, thus preventing their usage in many real-world applications. To address these limitations, we present an approach to change the appearance of a high-resolution image using ethnicity-specific aging information and weak spatial supervision to guide…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Portrait editing is a popular subject in photo manipulation. The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in existing techniques: diversity, quality, and controllability for portrait synthesis and editing. To address these issues, we propose a novel end-to-end learning framework that leverages conditional GANs guided by provided face masks for generating faces. The framework learns feature embeddings for every face component (e.g., mouth, hair, eye), separately, contributing to bette…
Existing conditional image synthesis frameworks generate images based on user inputs in a single modality, such as text, segmentation, sketch, or style reference. They are often unable to leverage multimodal user inputs when available, which reduces their practicality. To address this limitation, we propose the Product-of-Experts Generative Adversarial Networks (PoE-GAN) framework, which can synthesize images conditioned on multiple input modalities or any subset of them, even the empty set. PoE-GAN consists of a product-of-experts generator and a multimodal multiscale projection discriminator…
University of California, Los Angeles（加州大学洛杉矶分校）；Google Brain（谷歌大脑）
Conditional GANs are at the forefront of natural image synthesis. The main drawback of such models is the necessity for labeled data. In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, and take a step towards bridging the gap between conditional and unconditional GANs. In particular, we allow the networks to collaborate on the task of representation learning, while being adversarial with respect to the classic GAN game. The role of self-supervision is to encourage the discriminator to learn meaningful feature representations which a…
In cases where a Wasserstein GAN depends on a condition the latter is usually handled via an expectation within the loss function. Depending on the way this is motivated, the discriminator is either required to be Lipschitz-1 in both or in only one of its arguments. For the weaker requirement to become usable one needs to exchange a supremum and an expectation. This is a mathematically perilous operation, which is, so far, only partially justified in the literature. This short mathematical note intends to fill this gap and provides the mathematical rationale for discriminators that are only pa…
TU Dortmund University（多特蒙德工业大学）；EPFL（洛桑联邦理工学院）；University of Wuppertal（伍珀塔尔大学）
We present an approach to quantifying both aleatoric and epistemic uncertainty for deep neural networks in image classification, based on generative adversarial networks (GANs). While most works in the literature that use GANs to generate out-of-distribution (OoD) examples only focus on the evaluation of OoD detection, we present a GAN based approach to learn a classifier that produces proper uncertainties for OoD examples as well as for false positives (FPs). Instead of shielding the entire in-distribution data with GAN generated OoD examples which is state-of-the-art, we shield each class se…
Generative Adversarial Networks (GANs) are able to learn mappings between simple, relatively low-dimensional, random distributions and points on the manifold of realistic images in image-space. The semantics of this mapping, however, are typically entangled such that meaningful image properties cannot be controlled independently of one another. Conditional GANs (cGANs) provide a potential solution to this problem, allowing specific semantics to be enforced during training. This solution, however, depends on the availability of precise labels, which are sometimes difficult or near impossible to…
Harvard University（哈佛大学）；Massachusetts Institute of Technology（麻省理工学院）
We introduce the decision-aware time-series conditional generative adversarial network (DAT-CGAN) as a method for time-series generation. The framework adopts a multi-Wasserstein loss on structured decision-related quantities, capturing the heterogeneity of decision-related data and providing new effectiveness in supporting the decision processes of end users. We improve sample efficiency through an overlapped block-sampling method, and provide a theoretical characterization of the generalization properties of DAT-CGAN. The framework is demonstrated on financial time series for a multi-time-st…
When trained on multimodal image datasets, normal Generative Adversarial Networks (GANs) are usually outperformed by class-conditional GANs and ensemble GANs, but conditional GANs is restricted to labeled datasets and ensemble GANs lack efficiency. We propose a novel GAN variant called virtual conditional GAN (vcGAN) which is not only an ensemble GAN with multiple generative paths while adding almost zero network parameters, but also a conditional GAN that can be trained on unlabeled datasets without explicit clustering steps or objectives other than the adversary loss. Inside the vcGAN's gene…
University of Southern California（南加州大学）；Stanford University（斯坦福大学）
In this work, we train conditional Wasserstein generative adversarial networks to effectively sample from the posterior of physics-based Bayesian inference problems. The generator is constructed using a U-Net architecture, with the latent information injected using conditional instance normalization. The former facilitates a multiscale inverse map, while the latter enables the decoupling of the latent space dimension from the dimension of the measurement, and introduces stochasticity at all scales of the U-Net. We solve PDE-based inverse problems to demonstrate the performance of our approach …
Automatic analysis of spatio-temporal microscopy images is inevitable for state-of-the-art research in the life sciences. Recent developments in deep learning provide powerful tools for automatic analyses of such image data, but heavily depend on the amount and quality of provided training data to perform well. To this end, we developed a new method for realistic generation of synthetic 2D+t microscopy image data of fluorescently labeled cellular nuclei. The method combines spatiotemporal statistical shape models of different cell cycle stages with a conditional GAN to generate time series of …
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by introducing progressive pruning residual block (PP-Res) and class-aware distillation. The PP-Res is an extension of the conventional residual block where each convolutional layer is followed by a learnable mask layer to progressively prune network parameters as training proceeds. The class-aware distillation, on the other hand, enhances the stability of training b…
Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization
School of Artificial Intelligence/School of Future Technology, Nanjing University of Information Science & Technology, Nanjing, China（人工智能学院/未来技术学院，南京信息科学技术大学）；Perceptual and Generative AI Lab, Nanjing University of Information Science & Technology, Nanjing, China（感知与生成人工智能实验室，南京信息科学技术大学）；College of Media, Zhejiang University, Hangzhou, China（传媒学院，浙江大学）；College of Computer Science and Technology, Zhejiang University, Hangzhou, China（计算机科学与技术学院，浙江大学）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Adobe Research（Adobe研究）
We introduce a simple but effective unsupervised method for generating realistic and diverse images. We train a class-conditional GAN model without using manually annotated class labels. Instead, our model is conditional on labels automatically derived from clustering in the discriminator's feature space. Our clustering step automatically discovers diverse modes, and explicitly requires the generator to cover them. Experiments on standard mode collapse benchmarks show that our method outperforms several competing methods when addressing mode collapse. Our method also performs well on large-sca…
Purdue University（普渡大学）；Politecnico di Milano（米兰理工大学）
The widespread availability of image editing tools and improvements in image processing techniques allow image manipulation to be very easy. Oftentimes, easy-to-use yet sophisticated image manipulation tools yields distortions/changes imperceptible to the human observer. Distribution of forged images can have drastic ramifications, especially when coupled with the speed and vastness of the Internet. Therefore, verifying image integrity poses an immense and important challenge to the digital forensic community. Satellite images specifically can be modified in a number of ways, including the ins…
University of Maryland, College Park（马里兰大学学院公园分校）；Massachusetts Institute of Technology（麻省理工学院）
Generative Adversarial Networks (GANs) are modern methods to learn the underlying distribution of a data set. GANs have been widely used in sample synthesis, de-noising, domain transfer, etc. GANs, however, are designed in a model-free fashion where no additional information about the underlying distribution is available. In many applications, however, practitioners have access to the underlying independence graph of the variables, either as a Bayesian network or a Markov Random Field (MRF). We ask: how can one use this additional information in designing model-based GANs? In this paper, we pr…
Recent advances in conditional image generation tasks, such as image-to-image translation and image inpainting, are largely accounted to the success of conditional GAN models, which are often optimized by the joint use of the GAN loss with the reconstruction loss. However, we reveal that this training recipe shared by almost all existing methods causes one critical side effect: lack of diversity in output samples. In order to accomplish both training stability and multimodal output generation, we propose novel training schemes with a new set of losses named moment reconstruction losses that si…
University of Guelph（圭尔夫大学）；Vector Institute（向量研究所）；Facebook AI Research（Facebook人工智能研究）
Conditional Generative Adversarial Networks (cGANs) are finding increasingly widespread use in many application domains. Despite outstanding progress, quantitative evaluation of such models often involves multiple distinct metrics to assess different desirable properties, such as image quality, conditional consistency, and intra-conditioning diversity. In this setting, model benchmarking becomes a challenge, as each metric may indicate a different "best" model. In this paper, we propose the Frechet Joint Distance (FJD), which is defined as the Frechet distance between joint distributions of im…
Few-Shot Learning with Adaptive Weight Masking in Conditional GANs
Tulane University（杜兰大学）；Northeastern University（东北大学）；Washington University in St. Louis（华盛顿大学圣路易斯分校）；New York University（纽约大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
New York University（纽约大学）；IT University of Copenhagen（哥本哈根信息技术大学）
Generative Adversarial Networks (GANs) have shown im-pressive results for image generation. However, GANs facechallenges in generating contents with certain types of con-straints, such as game levels. Specifically, it is difficult togenerate levels that have aesthetic appeal and are playable atthe same time. Additionally, because training data usually islimited, it is challenging to generate unique levels with cur-rent GANs. In this paper, we propose a new GAN architec-ture namedConditional Embedding Self-Attention Genera-tive Adversarial Network(CESAGAN) and a new bootstrap-ping training proc…
