2022-06-25 更新
Making Generated Images Hard To Spot: A Transferable Attack On Synthetic Image Detectors
Authors:Xinwei Zhao, Matthew C. Stamm
Visually realistic GAN-generated images have recently emerged as an important misinformation threat. Research has shown that these synthetic images contain forensic traces that are readily identifiable by forensic detectors. Unfortunately, these detectors are built upon neural networks, which are vulnerable to recently developed adversarial attacks. In this paper, we propose a new anti-forensic attack capable of fooling GAN-generated image detectors. Our attack uses an adversarially trained generator to synthesize traces that these detectors associate with real images. Furthermore, we propose a technique to train our attack so that it can achieve transferability, i.e. it can fool unknown CNNs that it was not explicitly trained against. We evaluate our attack through an extensive set of experiments, where we show that our attack can fool eight state-of-the-art detection CNNs with synthetic images created using seven different GANs, and outperform other alternative attacks.
PDF
论文截图
GAN2X: Non-Lambertian Inverse Rendering of Image GANs
Authors:Xingang Pan, Ayush Tewari, Lingjie Liu, Christian Theobalt
2D images are observations of the 3D physical world depicted with the geometry, material, and illumination components. Recovering these underlying intrinsic components from 2D images, also known as inverse rendering, usually requires a supervised setting with paired images collected from multiple viewpoints and lighting conditions, which is resource-demanding. In this work, we present GAN2X, a new method for unsupervised inverse rendering that only uses unpaired images for training. Unlike previous Shape-from-GAN approaches that mainly focus on 3D shapes, we take the first attempt to also recover non-Lambertian material properties by exploiting the pseudo paired data generated by a GAN. To achieve precise inverse rendering, we devise a specularity-aware neural surface representation that continuously models the geometry and material properties. A shading-based refinement technique is adopted to further distill information in the target image and recover more fine details. Experiments demonstrate that GAN2X can accurately decompose 2D images to 3D shape, albedo, and specular properties for different object categories, and achieves the state-of-the-art performance for unsupervised single-view 3D face reconstruction. We also show its applications in downstream tasks including real image editing and lifting 2D GANs to decomposed 3D GANs.
PDF The video demo is available at the project page: https://people.mpi-inf.mpg.de/~xpan/GAN2X/
论文截图
Applications of Generative Adversarial Networks in Neuroimaging and Clinical Neuroscience
Authors:Rongguang Wang, Vishnu Bashyam, Zhijian Yang, Fanyang Yu, Vasiliki Tassopoulou, Lasya P. Sreepada, Sai Spandana Chintapalli, Dushyant Sahoo, Ioanna Skampardoni, Konstantina Nikita, Ahmed Abdulkadir, Junhao Wen, Christos Davatzikos
Generative adversarial networks (GANs) are one powerful type of deep learning models that have been successfully utilized in numerous fields. They belong to a broader family called generative methods, which generate new data with a probabilistic model by learning sample distribution from real examples. In the clinical context, GANs have shown enhanced capabilities in capturing spatially complex, nonlinear, and potentially subtle disease effects compared to traditional generative methods. This review appraises the existing literature on the applications of GANs in imaging studies of various neurological conditions, including Alzheimer’s disease, brain tumors, brain aging, and multiple sclerosis. We provide an intuitive explanation of various GAN methods for each application and further discuss the main challenges, open questions, and promising future directions of leveraging GANs in neuroimaging. We aim to bridge the gap between advanced deep learning methods and neurology research by highlighting how GANs can be leveraged to support clinical decision making and contribute to a better understanding of the structural and functional patterns of brain diseases.
PDF
论文截图
StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis
Authors:Minguk Kang, Joonghyuk Shin, Jaesik Park
Generative Adversarial Network (GAN) is one of the state-of-the-art generative models for realistic image synthesis. While training and evaluating GAN becomes increasingly important, the current GAN research ecosystem does not provide reliable benchmarks for which the evaluation is conducted consistently and fairly. Furthermore, because there are few validated GAN implementations, researchers devote considerable time to reproducing baselines. We study the taxonomy of GAN approaches and present a new open-source library named StudioGAN. StudioGAN supports 7 GAN architectures, 9 conditioning methods, 4 adversarial losses, 13 regularization modules, 3 differentiable augmentations, 7 evaluation metrics, and 5 evaluation backbones. With our training and evaluation protocol, we present a large-scale benchmark using various datasets (CIFAR10, ImageNet, AFHQv2, FFHQ, and Baby/Papa/Granpa-ImageNet) and 3 different evaluation backbones (InceptionV3, SwAV, and Swin Transformer). Unlike other benchmarks used in the GAN community, we train representative GANs, including BigGAN, StyleGAN2, and StyleGAN3, in a unified training pipeline and quantify generation performance with 7 evaluation metrics. The benchmark evaluates other cutting-edge generative models(e.g., StyleGAN-XL, ADM, MaskGIT, and RQ-Transformer). StudioGAN provides GAN implementations, training, and evaluation scripts with the pre-trained weights. StudioGAN is available at https://github.com/POSTECH-CVLab/PyTorch-StudioGAN.
PDF 30 pages, Submitted to journal
论文截图
SOS: Score-based Oversampling for Tabular Data
Authors:Jayoung Kim, Chaejeong Lee, Yehjin Shin, Sewon Park, Minjung Kim, Noseong Park, Jihoon Cho
Score-based generative models (SGMs) are a recent breakthrough in generating fake images. SGMs are known to surpass other generative models, e.g., generative adversarial networks (GANs) and variational autoencoders (VAEs). Being inspired by their big success, in this work, we fully customize them for generating fake tabular data. In particular, we are interested in oversampling minor classes since imbalanced classes frequently lead to sub-optimal training outcomes. To our knowledge, we are the first presenting a score-based tabular data oversampling method. Firstly, we re-design our own score network since we have to process tabular data. Secondly, we propose two options for our generation method: the former is equivalent to a style transfer for tabular data and the latter uses the standard generative policy of SGMs. Lastly, we define a fine-tuning method, which further enhances the oversampling quality. In our experiments with 6 datasets and 10 baselines, our method outperforms other oversampling methods in all cases.
PDF Accepted by KDD 2022
论文截图
Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing
Authors:Gaurav Parmar, Yijun Li, Jingwan Lu, Richard Zhang, Jun-Yan Zhu, Krishna Kumar Singh
Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the “invertibility” of different image segments and project each segment into a latent layer. Easier regions can be inverted into an earlier layer in the generator’s latent space, while more challenging regions can be inverted into a later feature space. Experiments show that our method obtains better inversion results compared to the recent approaches on complex categories, while maintaining downstream editability. Please refer to our project page at https://www.cs.cmu.edu/~SAMInversion.
PDF CVPR 2022. Github: https://github.com/adobe-research/sam_inversion Website: https://www.cs.cmu.edu/~SAMInversion
论文截图
Convex space learning improves deep-generative oversampling for tabular imbalanced classification on smaller datasets
Authors:Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Data is commonly stored in tabular format. Several fields of research (e.g., biomedical, fault/fraud detection), are prone to small imbalanced tabular data. Supervised Machine Learning on such data is often difficult due to class imbalance, adding further to the challenge. Synthetic data generation i.e. oversampling is a common remedy used to improve classifier performance. State-of-the-art linear interpolation approaches, such as LoRAS and ProWRAS can be used to generate synthetic samples from the convex space of the minority class to improve classifier performance in such cases. Generative Adversarial Networks (GANs) are common deep learning approaches for synthetic sample generation. Although GANs are widely used for synthetic image generation, their scope on tabular data in the context of imbalanced classification is not adequately explored. In this article, we show that existing deep generative models perform poorly compared to linear interpolation approaches generating synthetic samples from the convex space of the minority class, for imbalanced classification problems on tabular datasets of small size. We propose a deep generative model, ConvGeN combining the idea of convex space learning and deep generative models. ConVGeN learns the coefficients for the convex combinations of the minority class samples, such that the synthetic data is distinct enough from the majority class. We demonstrate that our proposed model ConvGeN improves imbalanced classification on such small datasets, as compared to existing deep generative models while being at par with the existing linear interpolation approaches. Moreover, we discuss how our model can be used for synthetic tabular data generation in general, even outside the scope of data imbalance, and thus, improves the overall applicability of convex space learning.
PDF
论文截图
GR-GAN: Gradual Refinement Text-to-image Generation
Authors:Bo Yang, Fangxiang Feng, Xiaojie Wang
A good Text-to-Image model should not only generate high quality images, but also ensure the consistency between the text and the generated image. Previous models failed to simultaneously fix both sides well. This paper proposes a Gradual Refinement Generative Adversarial Network (GR-GAN) to alleviates the problem efficiently. A GRG module is designed to generate images from low resolution to high resolution with the corresponding text constraints from coarse granularity (sentence) to fine granularity (word) stage by stage, a ITM module is designed to provide image-text matching losses at both sentence-image level and word-region level for corresponding stages. We also introduce a new metric Cross-Model Distance (CMD) for simultaneously evaluating image quality and image-text consistency. Experimental results show GR-GAN significant outperform previous models, and achieve new state-of-the-art on both FID and CMD. A detailed analysis demonstrates the efficiency of different generation stages in GR-GAN.
PDF Accepted by ICME 2022
论文截图