2022-11-05 更新
ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data
Authors:Jie Cao, Mandi Luo, Junchi Yu, Ming-Hsuan Yang, Ran He
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.
PDF
点此查看论文截图
On the detection of synthetic images generated by diffusion models
Authors:Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, Luisa Verdoliva
Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-networks scenarios involving image compression and resizing. Datasets and code are available at github.com/grip-unina/DMimageDetection.
PDF
点此查看论文截图
Progressive Transformation Learning For Leveraging Virtual Images in Training
Authors:Yi-Ting Shen, Hyungtae Lee, Heesung Kwon, Shuvra Shikhar Bhattacharyya
To effectively interrogate UAV-based images for detecting objects of interest, such as humans, it is essential to acquire large-scale UAV-based datasets that include human instances with various poses captured from widely varying viewing angles. As a viable alternative to laborious and costly data curation, we introduce Progressive Transformation Learning (PTL), which gradually augments a training dataset by adding transformed virtual images with enhanced realism. Generally, a virtual2real transformation generator in the conditional GAN framework suffers from quality degradation when a large domain gap exists between real and virtual images. To deal with the domain gap, PTL takes a novel approach that progressively iterates the following three steps: 1) select a subset from a pool of virtual images according to the domain gap, 2) transform the selected virtual images to enhance realism, and 3) add the transformed virtual images to the training set while removing them from the pool. In PTL, accurately quantifying the domain gap is critical. To do that, we theoretically demonstrate that the feature representation space of a given object detector can be modeled as a multivariate Gaussian distribution from which the Mahalanobis distance between a virtual object and the Gaussian distribution of each object category in the representation space can be readily computed. Experiments show that PTL results in a substantial performance increase over the baseline, especially in the small data and the cross-domain regime.
PDF
点此查看论文截图
Comparative analysis of segmentation and generative models for fingerprint retrieval task
Authors:Megh Patel, Devarsh Patel, Sarthak Patel
Biometric Authentication like Fingerprints has become an integral part of the modern technology for authentication and verification of users. It is pervasive in more ways than most of us are aware of. However, these fingerprint images deteriorate in quality if the fingers are dirty, wet, injured or when sensors malfunction. Therefore, extricating the original fingerprint by removing the noise and inpainting it to restructure the image is crucial for its authentication. Hence, this paper proposes a deep learning approach to address these issues using Generative (GAN) and Segmentation models. Qualitative and Quantitative comparison has been done between pix2pixGAN and cycleGAN (generative models) as well as U-net (segmentation model). To train the model, we created our own dataset NFD - Noisy Fingerprint Dataset meticulously with different backgrounds along with scratches in some images to make it more realistic and robust. In our research, the u-net model performed better than the GAN networks
PDF This is a working draft and not indented for publication
点此查看论文截图