Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial networks (GANs). Recently, GANs are utilized as the training sample generator when obtaining or storing real training data is expensive even infeasible. However, traditional GANs generated images are not as informative as the real training samples when being used to train deep neural networks. In this paper, we propose a novel method to synthesize Informative Training samples with GAN (IT-GAN). Specifically, we freeze a pre-trained GAN model and learn the informative latent vectors that correspond to informative training samples. The synthesized images are required to preserve information for training deep neural networks rather than visual reality or fidelity. Experiments verify that the deep neural networks can learn faster and achieve better performance when being trained with our IT-GAN generated images. We also show that our method is a promising solution to dataset condensation problem.

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset condensation that aims to replace the original large training set with a significantly smaller learned synthetic set while preserving the original information. While training deep models on the small set of condensed images can be extremely fast, their synthesis remains computationally expensive due to the complex bi-level optimization and second-order derivative computation. In this work, we propose a simple yet effective method that synthesizes condensed images by matching feature distributions of the synthetic and original training images in many sampled embedding spaces. Our method significantly reduces the synthesis cost while achieving comparable or better performance. Thanks to its efficiency, we apply our method to more realistic and larger datasets with sophisticated neural architectures and obtain a significant performance boost. We also show promising practical benefits of our method in continual learning and neural architecture search.

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 invariant to semantic-preserving transformations through a network before they are distilled into the student network. We span the distilled representation of the synthetic domain to the real domain by also using real training data to remedy the mode collapse of GANs and boost the student network performance in a real domain. Experiments justify the efficacy of our method and reveal its great significance in self-supervised representation learning. Code is available at https://github.com/yangyu12/squeeze-and-span.

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller and high-quality synthetic datasets from large ones. Existing DD methods based on gradient matching achieve leading performance; however, they are extremely computationally intensive as they require continuously optimizing a dataset among thousands of randomly initialized models. In this paper, we assume that training the synthetic data with diverse models leads to better generalization performance. Thus we propose two \textbf{model augmentation} techniques, ~\ie using \textbf{early-stage models} and \textbf{weight perturbation} to learn an informative synthetic set with significantly reduced training cost. Extensive experiments demonstrate that our method achieves up to 20$\times$ speedup and comparable performance on par with state-of-the-art baseline methods.

最近的研究表明，基于梯度匹配的数据集综合或数据集凝结（DC），当应用于数据有效的学习任务时，方法可以实现最先进的性能。但是，在这项研究中，我们证明，当任务 - 核定信息构成培训数据集的重要组成部分时，现有的DC方法比随机选择方法的性能更糟。我们将其归因于缺乏与课堂梯度匹配策略所产生的类对比信号的参与。为了解决此问题，我们通过修改损耗函数以使DC方法有效地捕获类之间的差异来提出与对比度信号（DCC）的数据集凝结。此外，我们通过跟踪内核速度来分析训练动力学的新损失函数。此外，我们引入了双层热身策略，以稳定优化。我们的实验结果表明，尽管现有方法对细粒度的图像分类任务无效，但所提出的方法可以成功地为相同任务生成信息合成数据集。此外，我们证明所提出的方法甚至在基准数据集（例如SVHN，CIFAR-10和CIFAR-100）上也优于基准。最后，我们通过将其应用于持续学习任务来证明该方法的高度适用性。

The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part segmentation tasks by generating high-quality images with a pre-trained GAN and labelling the generated images with an automatic annotator. In particular, we formulate the annotator learning as a learning-to-learn problem. Given a pre-trained GAN, the annotator learns to label object parts in a set of randomly generated images such that a part segmentation model trained on these synthetic images with their predicted labels obtains low segmentation error on a small validation set of manually labelled images. We further reduce this nested-loop optimization problem to a simple gradient matching problem and efficiently solve it with an iterative algorithm. We show that our method can learn annotators from a broad range of labelled images including real images, generated images, and even analytically rendered images. Our method is evaluated with semi-supervised part segmentation tasks and significantly outperforms other semi-supervised competitors when the amount of labelled examples is extremely limited.

知识蒸馏在模型压缩方面取得了显着的成就。但是，大多数现有方法需要原始的培训数据，而实践中的实际数据通常是不可用的，因为隐私，安全性和传输限制。为了解决这个问题，我们提出了一种有条件的生成数据无数据知识蒸馏（CGDD）框架，用于培训有效的便携式网络，而无需任何实际数据。在此框架中，除了使用教师模型中提取的知识外，我们将预设标签作为额外的辅助信息介绍以培训发电机。然后，训练有素的发生器可以根据需要产生指定类别的有意义的培训样本。为了促进蒸馏过程，除了使用常规蒸馏损失，我们将预设标签视为地面真理标签，以便学生网络直接由合成训练样本类别监督。此外，我们强制学生网络模仿教师模型的注意图，进一步提高了其性能。为了验证我们方法的优越性，我们设计一个新的评估度量称为相对准确性，可以直接比较不同蒸馏方法的有效性。培训的便携式网络通过提出的数据无数据蒸馏方法获得了99.63％，99.07％和99.84％的CIFAR10，CIFAR100和CALTECH101的相对准确性。实验结果表明了所提出的方法的优越性。

无数据知识蒸馏（DFKD）最近引起了人们的关注，这要归功于其在不使用培训数据的情况下将知识从教师网络转移到学生网络的吸引力。主要思想是使用发电机合成数据以培训学生。随着发电机的更新，合成数据的分布将发生变化。如果发电机和学生接受对手的训练，使学生忘记了先前一步获得的知识，则这种分配转换可能会很大。为了减轻这个问题，我们提出了一种简单而有效的方法，称为动量对抗蒸馏（MAD），该方法维持了发电机的指数移动平均值（EMA）副本，并使用发电机和EMA生成器的合成样品来培训学生。由于EMA发电机可以被视为发电机旧版本的合奏，并且与发电机相比，更新的更改通常会发生较小的变化，因此对其合成样本进行培训可以帮助学生回顾过去的知识，并防止学生适应太快的速度发电机的新更新。我们在六个基准数据集上进行的实验，包括ImageNet和Place365，表明MAD的性能优于竞争方法来处理大型分配转移问题。我们的方法还与现有的DFKD方法相比，甚至在某些情况下达到了最新的方法。

我们研究了GaN调理问题，其目标是使用标记数据将普雷雷尼的无条件GaN转换为条件GaN。我们首先识别并分析这一问题的三种方法 - 从头开始​​，微调和输入重新编程的条件GaN培训。我们的分析表明，当标记数据的数量很小时，输入重新编程执行最佳。通过稀缺标记数据的现实世界情景，我们专注于输入重编程方法，并仔细分析现有算法。在识别出先前输入重新编程方法的一些关键问题之后，我们提出了一种名为INREP +的新算法。我们的算法INREP +解决了现有问题，具有可逆性神经网络的新颖用途和正面未标记（PU）学习。通过广泛的实验，我们表明Inrep +优于所有现有方法，特别是当标签信息稀缺，嘈杂和/或不平衡时。例如，对于用1％标记数据调节CiFar10 GaN的任务，Inrep +实现了82.13的平均峰值，而第二个最佳方法达到114.51。

数据集凝结是一种新兴的技术，旨在学习一个微小的数据集，该数据集捕获原始数据集中编码的丰富信息。随着数据集的大小当代机器学习模型的依赖变得越来越大，凝结方法成为加速网络培训和减少数据存储的重要方向。尽管在这个快速增长的领域中提出了许多方法，但评估和比较不同的冷凝方法是非平凡的，仍然仍然是一个空旷的问题。凝结数据集的质量通常会受到许多关键的影响最终性能的关键因素，例如数据增强和模型架构。缺乏评估和比较冷凝方法的系统方法不仅阻碍了我们对现有技术的理解，而且还阻碍了合成数据集的实际用法。这项工作提供了数据集冷凝的第一个大规模标准化基准。它由一套评估组成，可以全面地通过其生成的数据集的镜头来全面反映冷凝方法的生成性和有效性。利用这一基准，我们对当前的冷凝方法进行了大规模研究，并报告了许多有见地的发现，为未来发展开辟了新的可能性。开源的基准库，包括评估人员，基线方法和生成的数据集，以促进未来的研究和应用。

Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-specific augmentation techniques. Despite the effectiveness, it is difficult for these methods to scale to practical applications. In this work, we present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks. We first produce augmented samples using the convex combinations of the real samples. Then, we optimize the augmented samples by minimizing the norms of the data scores, i.e., the gradients of the log-density functions. This procedure enforces the augmented samples close to the data manifold. To estimate the scores, we train a deep estimation network with multi-scale score matching. For different image synthesis tasks, we train the score estimation network using different data. We do not require the tuning of the hyperparameters or modifications to the network architecture. The ScoreMix method effectively increases the diversity of data and reduces the overfitting problem. Moreover, it can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ScoreMix method achieve significant improvements.

旨在选择最有用的培训样本子集的CoreSet选择是一个长期存在的学习问题，可以使许多下游任务受益，例如数据效率学习，持续学习，神经体系结构搜索，主动学习等。但是，许多现有的核心选择方法不是为深度学习而设计的，这些方法可能具有很高的复杂性和不良的概括性能。此外，最近提出的方法在模型，数据集和不同复杂性的设置上进行评估。为了促进深度学习中核心选择的研究，我们贡献了一个全面的代码库，即深核，并就CIFAR10和Imagenet数据集的流行核心选择方法提供了经验研究。关于CIFAR10和Imagenet数据集的广泛实验验证，尽管在某些实验设置中具有优势，但随机选择仍然是一个强大的基线。

生成照片 - 现实图像，语义编辑和表示学习是高分辨率生成模型的许多潜在应用中的一些。最近在GAN的进展将它们建立为这些任务的绝佳选择。但是，由于它们不提供推理模型，因此使用GaN潜在空间无法在实际图像上完成诸如分类的图像编辑或下游任务。尽管培训了训练推理模型或设计了一种迭代方法来颠覆训练有素的发生器，但之前的方法是数据集（例如人类脸部图像）和架构（例如样式）。这些方法是非延伸到新型数据集或架构的。我们提出了一般框架，该框架是不可知的架构和数据集。我们的主要识别是，通过培训推断和生成模型在一起，我们允许它们彼此适应并收敛到更好的质量模型。我们的\ textbf {invang}，可逆GaN的简短，成功将真实图像嵌入到高质量的生成模型的潜在空间。这使我们能够执行图像修复，合并，插值和在线数据增强。我们展示了广泛的定性和定量实验。

近年来有条件的GAN已经成熟，并且能够产生高质量的现实形象。但是，计算资源和培训高质量的GAN所需的培训数据是巨大的，因此对这些模型的转移学习的研究是一个紧急话题。在本文中，我们探讨了从高质量预训练的无条件GAN到有条件的GAN的转移。为此，我们提出了基于HyperNetwork的自适应权重调制。此外，我们介绍了一个自我初始化过程，不需要任何真实数据才能初始化HyperNetwork参数。为了进一步提高知识转移的样本效率，我们建议使用自我监督（对比）损失来改善GaN判别者。在广泛的实验中，我们验证了多个标准基准上的Hypernetworks，自我初始化和对比损失的效率。

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semantics including color, spatial coherence, textures, and high-level concepts. This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images. As shown in Fig. 1, the deep generative prior (DGP) provides compelling results to restore missing semantics, e.g., color, patch, resolution, of various degraded images. It also enables diverse image manipulation including random jittering, image morphing, and category transfer. Such highly flexible restoration and manipulation are made possible through relaxing the assumption of existing GAN-inversion methods, which tend to fix the generator. Notably, we allow the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN. We show that these easy-to-implement and practical changes help preserve the reconstruction to remain in the manifold of nature image, and thus lead to more precise and faithful reconstruction for real images. Code is available at https://github.com/XingangPan/deepgenerative-prior.

生成对抗网络（GAN）具有许多潜在的医学成像应用，包括数据扩展，域适应和模型解释。由于图形处理单元（GPU）的记忆力有限，因此在低分辨率的医学图像上对当前的3D GAN模型进行了训练，因此这些模型要么无法扩展到高分辨率，要么容易出现斑驳的人工制品。在这项工作中，我们提出了一种新颖的端到端GAN体系结构，可以生成高分辨率3D图像。我们通过使用训练和推理之间的不同配置来实现这一目标。在训练过程中，我们采用了层次结构，该结构同时生成图像的低分辨率版本和高分辨率图像的随机选择子量。层次设计具有两个优点：首先，对高分辨率图像训练的记忆需求在子量之间摊销。此外，将高分辨率子体积固定在单个低分辨率图像上可确保子量化之间的解剖一致性。在推断期间，我们的模型可以直接生成完整的高分辨率图像。我们还将具有类似层次结构的编码器纳入模型中，以从图像中提取特征。 3D胸CT和脑MRI的实验表明，我们的方法在图像生成中的表现优于最新技术。我们还证明了所提出的模型在数据增强和临床相关特征提取中的临床应用。

由于大型数据集中的深度学习模型需要大量时间和资源，因此希望构建一个小型合成数据集，我们可以通过该数据集充分训练深度学习模型。最近有一些作品通过复杂的BI级优化探索了有关凝结图像数据集的解决方案。例如，数据集冷凝（DC）匹配网络梯度W.R.T.大型数据和小合成数据，在每个外迭代处，网络权重优化了多个步骤。但是，现有方法具有其固有的局限性：（1）它们不直接适用于数据离散的图表； （2）由于所涉及的嵌套优化，冷凝过程在计算上昂贵。为了弥合差距，我们研究了针对图形数据集量身定制的有效数据集冷凝，在该数据集中我们将离散图结构模拟为概率模型。我们进一步提出了一个单步梯度匹配方案，该方案仅执行一个步骤，而无需训练网络权重。我们的理论分析表明，该策略可以生成合成图，从而导致实际图上的分类损失降低。各种图数据集的广泛实验证明了该方法的有效性和效率。特别是，我们能够将数据集大小降低90％，同时大约98％的原始性能，并且我们的方法明显快于多步梯度匹配（例如，CIFAR10中的15倍用于合成500个图）。

组织病理学分析是对癌前病变诊断的本金标准。从数字图像自动组织病理学分类的目标需要监督培训，这需要大量的专家注释，这可能是昂贵且耗时的收集。同时，精确分类从全幻灯片裁剪的图像斑块对于基于标准滑动窗口的组织病理学幻灯片分类方法是必不可少的。为了减轻这些问题，我们提出了一个精心设计的条件GaN模型，即hostogan，用于在类标签上合成现实组织病理学图像补丁。我们还研究了一种新颖的合成增强框架，可选择地添加由我们提出的HADOGAN生成的新的合成图像补丁，而不是直接扩展与合成图像的训练集。通过基于其指定标签的置信度和实际标记图像的特征相似性选择合成图像，我们的框架为合成增强提供了质量保证。我们的模型在两个数据集上进行评估：具有有限注释的宫颈组织病理学图像数据集，以及具有转移性癌症的淋巴结组织病理学图像的另一个数据集。在这里，我们表明利用具有选择性增强的组织产生的图像导致对宫颈组织病理学和转移性癌症数据集分别的分类性能（分别为6.7％和2.8％）的显着和一致性。

Differentially private data generation techniques have become a promising solution to the data privacy challenge -- it enables sharing of data while complying with rigorous privacy guarantees, which is essential for scientific progress in sensitive domains. Unfortunately, restricted by the inherent complexity of modeling high-dimensional distributions, existing private generative models are struggling with the utility of synthetic samples. In contrast to existing works that aim at fitting the complete data distribution, we directly optimize for a small set of samples that are representative of the distribution under the supervision of discriminative information from downstream tasks, which is generally an easier task and more suitable for private training. Our work provides an alternative view for differentially private generation of high-dimensional data and introduces a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.