Approximating Human Judgment of Generated Image Quality

Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches that do not correlate well with human judgment, such as the Inception Score and Fr\'echet Inception Distance. Real human labels have also been used in evaluation, but are inefficient and expensive to collect for each image. Here, we present a novel method to automatically evaluate images based on their quality as perceived by humans. By not only generating image embeddings from Inception network activations and comparing them to the activations for real images, of which other methods perform a variant, but also regressing the activation statistics to match gold standard human labels, we demonstrate 66% accuracy in predicting human scores of image realism, matching the human inter-rater agreement rate. Our approach also generalizes across generative models, suggesting the potential for capturing a model-agnostic measure of image quality. We open source our dataset of human labels for the advancement of research and techniques in this area.

FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRI

Leading neuroimaging studies have pushed 3T MRI acquisition resolutions below 1.0 mm for improved structure definition and morphometry. Yet, only few, time-intensive automated image analysis pipelines have been validated for high-resolution (HiRes) settings. Efficient deep learning approaches, on the other hand, rarely support more than one fixed resolution (usually 1.0 mm). Furthermore, the lack of a standard submillimeter resolution as well as limited availability of diverse HiRes data with sufficient coverage of scanner, age, diseases, or genetic variance poses additional, unsolved challenges for training HiRes networks. Incorporating resolution-independence into deep learning-based segmentation, i.e., the ability to segment images at their native resolution across a range of different voxel sizes, promises to overcome these challenges, yet no such approach currently exists. We now fill this gap by introducing a Voxelsize Independent Neural Network (VINN) for resolution-independent segmentation tasks and present FastSurferVINN, which (i) establishes and implements resolution-independence for deep learning as the first method simultaneously supporting 0.7-1.0 mm whole brain segmentation, (ii) significantly outperforms state-of-the-art methods across resolutions, and (iii) mitigates the data imbalance problem present in HiRes datasets. Overall, internal resolution-independence mutually benefits both HiRes and 1.0 mm MRI segmentation. With our rigorously validated FastSurferVINN we distribute a rapid tool for morphometric neuroimage analysis. The VINN architecture, furthermore, represents an efficient resolution-independent segmentation method for wider application

Information-theoretic stochastic contrastive conditional GAN: InfoSCC-GAN

Conditional generation is a subclass of generative problems where the output of the generation is conditioned by the attribute information. In this paper, we present a stochastic contrastive conditional generative adversarial network (InfoSCC-GAN) with an explorable latent space. The InfoSCC-GAN architecture is based on an unsupervised contrastive encoder built on the InfoNCE paradigm, an attribute classifier and an EigenGAN generator. We propose a novel training method, based on generator regularization using external or internal attributes every $n$-th iteration, using a pre-trained contrastive encoder and a pre-trained classifier. The proposed InfoSCC-GAN is derived based on an information-theoretic formulation of mutual information maximization between input data and latent space representation as well as latent space and generated data. Thus, we demonstrate a link between the training objective functions and the above information-theoretic formulation. The experimental results show that InfoSCC-GAN outperforms the "vanilla" EigenGAN in the image generation on AFHQ and CelebA datasets. In addition, we investigate the impact of discriminator architectures and loss functions by performing ablation studies. Finally, we demonstrate that thanks to the EigenGAN generator, the proposed framework enjoys a stochastic generation in contrast to vanilla deterministic GANs yet with the independent training of encoder, classifier, and generator in contrast to existing frameworks. Code, experimental results, and demos are available online at https://github.com/vkinakh/InfoSCC-GAN.

Measuring Complexity of Learning Schemes Using Hessian-Schatten Total-Variation

In this paper, we introduce the Hessian-Schatten total-variation (HTV) -- a novel seminorm that quantifies the total "rugosity" of multivariate functions. Our motivation for defining HTV is to assess the complexity of supervised learning schemes. We start by specifying the adequate matrix-valued Banach spaces that are equipped with suitable classes of mixed-norms. We then show that HTV is invariant to rotations, scalings, and translations. Additionally, its minimum value is achieved for linear mappings, supporting the common intuition that linear regression is the least complex learning model. Next, we present closed-form expressions for computing the HTV of two general classes of functions. The first one is the class of Sobolev functions with a certain degree of regularity, for which we show that HTV coincides with the Hessian-Schatten seminorm that is sometimes used as a regularizer for image reconstruction. The second one is the class of continuous and piecewise linear (CPWL) functions. In this case, we show that the HTV reflects the total change in slopes between linear regions that have a common facet. Hence, it can be viewed as a convex relaxation (l1-type) of the number of linear regions (l0-type) of CPWL mappings. Finally, we illustrate the use of our proposed seminorm with some concrete examples.

Evaluating Gradient Inversion Attacks and Defenses in Federated Learning

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the clients' private data. This paper evaluates existing attacks and defenses. We find that some attacks make strong assumptions about the setup. Relaxing such assumptions can substantially weaken these attacks. We then evaluate the benefits of three proposed defense mechanisms against gradient inversion attacks. We show the trade-offs of privacy leakage and data utility of these defense methods, and find that combining them in an appropriate manner makes the attack less effective, even under the original strong assumptions. We also estimate the computation cost of end-to-end recovery of a single image under each evaluated defense. Our findings suggest that the state-of-the-art attacks can currently be defended against with minor data utility loss, as summarized in a list of potential strategies. Our code is available at: https://github.com/Princeton-SysML/GradAttack.

WaveFake: A Data Set to Facilitate Audio Deepfake Detection

Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes" has emerged. This research most often focuses on the image domain, while studies exploring generated audio signals have, so-far, been neglected. In this paper we make three key contributions to narrow this gap. First, we provide researchers with an introduction to common signal processing techniques used for analyzing audio signals. Second, we present a novel data set, for which we collected nine sample sets from five different network architectures, spanning two languages. Finally, we supply practitioners with two baseline models, adopted from the signal processing community, to facilitate further research in this area.

360MonoDepth: High-Resolution 360° Monocular Depth Estimation

360{\deg} cameras can capture complete environments in a single shot, which makes 360{\deg} imagery alluring in many computer vision tasks. However, monocular depth estimation remains a challenge for 360{\deg} data, particularly for high resolutions like 2K (2048$\times$1024) that are important for novel-view synthesis and virtual reality applications. Current CNN-based methods do not support such high resolutions due to limited GPU memory. In this work, we propose a flexible framework for monocular depth estimation from high-resolution 360{\deg} images using tangent images. We project the 360{\deg} input image onto a set of tangent planes that produce perspective views, which are suitable for the latest, most accurate state-of-the-art perspective monocular depth estimators. We recombine the individual depth estimates using deformable multi-scale alignment followed by gradient-domain blending to improve the consistency of disparity estimates. The result is a dense, high-resolution 360{\deg} depth map with a high level of detail, also for outdoor scenes which are not supported by existing methods.

Predicting Poverty Level from Satellite Imagery using Deep Neural Networks

Determining the poverty levels of various regions throughout the world is crucial in identifying interventions for poverty reduction initiatives and directing resources fairly. However, reliable data on global economic livelihoods is hard to come by, especially for areas in the developing world, hampering efforts to both deploy services and monitor/evaluate progress. This is largely due to the fact that this data is obtained from traditional door-to-door surveys, which are time consuming and expensive. Overhead satellite imagery contain characteristics that make it possible to estimate the region's poverty level. In this work, I develop deep learning computer vision methods that can predict a region's poverty level from an overhead satellite image. I experiment with both daytime and nighttime imagery. Furthermore, because data limitations are often the barrier to entry in poverty prediction from satellite imagery, I explore the impact that data quantity and data augmentation have on the representational power and overall accuracy of the networks. Lastly, to evaluate the robustness of the networks, I evaluate them on data from continents that were absent in the development set.

Donut: Document Understanding Transformer without OCR

Understanding document images (e.g., invoices) has been an important research topic and has many applications in document processing automation. Through the latest advances in deep learning-based Optical Character Recognition (OCR), current Visual Document Understanding (VDU) systems have come to be designed based on OCR. Although such OCR-based approach promise reasonable performance, they suffer from critical problems induced by the OCR, e.g., (1) expensive computational costs and (2) performance degradation due to the OCR error propagation. In this paper, we propose a novel VDU model that is end-to-end trainable without underpinning OCR framework. To this end, we propose a new task and a synthetic document image generator to pre-train the model to mitigate the dependencies on large-scale real document images. Our approach achieves state-of-the-art performance on various document understanding tasks in public benchmark datasets and private industrial service datasets. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed model especially with consideration for a real-world application.

Audio Deepfake Perceptions in College Going Populations

Deepfake is content or material that is generated or manipulated using AI methods, to pass off as real. There are four different deepfake types: audio, video, image and text. In this research we focus on audio deepfakes and how people perceive it. There are several audio deepfake generation frameworks, but we chose MelGAN which is a non-autoregressive and fast audio deepfake generating framework, requiring fewer parameters. This study tries to assess audio deepfake perceptions among college students from different majors. This study also answers the question of how their background and major can affect their perception towards AI generated deepfakes. We also analyzed the results based on different aspects of: grade level, complexity of the grammar used in the audio clips, length of the audio clips, those who knew the term deepfakes and those who did not, as well as the political angle. It is interesting that the results show when an audio clip has a political connotation, it can affect what people think about whether it is real or fake, even if the content is fairly similar. This study also explores the question of how background and major can affect perception towards deepfakes.