[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

We explore the effect of dimensionality on the nearest neighbor problem. We show that under a broad set of conditions (much broader than independent and identically distributed dimensions), as dimensionality increases, the distance to the nearest data point approaches the distance to the farthest data point. To provide a practical perspective, we present empirical results on both real and synthetic data sets that demonstrate that this effect can occur for as few as 10-15 dimensions. These results should not be interpreted to mean that high-dimensional indexing is never meaningful; we illustrate this point by identifying some high-dimensional workloads for which this effect does not occur. However, our results do emphasize that the methodology used almost universally in the database literature to evaluate high-dimensional indexing techniques is flawed, and should be modified. In particular, most such techniques proposed in the literature are not evaluated versus simple linear scan, and are evaluated over workloads for which nearest neighbor is not meaningful. Often, even the reported experiments, when analyzed carefully, show that linear scan would outperform the techniques being proposed on the workloads studied in high (10-15) dimensionality!.

When is nearest neighbor meaningful

FPGAN: Face de-identification method with generative adversarial networks for social robots.

Biometric de-identification is an emerging topic of research within the information security domain that integrates privacy considerations with biometric system development. A comprehensive overview of research in the context of authentication applications spanning physiological, behavioral, and social-behavioral biometric systems and their privacy considerations is discussed. Three categories of biometric de-identification are introduced, namely complete de-identification, auxiliary biometric preserving de-identification, and traditional biometric preserving de-identification. An overview of biometric de-identification in emerging domains such as sensor-based biometrics, social behavioral biometrics, psychological user profile identification, and aesthetic-based biometrics is presented. The article concludes with open questions and provides a rich avenue for subsequent explorations of biometric de-identification in the context of information privacy.

Biometric Systems De-Identification: Current Advancements and Future Directions

In recent years, the security and privacy issues of face data in video surveillance have become one of the hotspots. How to protect privacy while maintaining the utility of monitored faces is a challenging problem. At present, most of the mainstream methods are suitable for maintaining data utility with respect to pre-defined criteria such as the structure similarity or shape of the face, which bears the criticism of poor versatility and adaptability. This paper proposes a novel generative framework called Quality Maintenance-Variational AutoEncoder (QM-VAE), which takes full advantage of existing privacy protection technologies. We innovatively add the loss of service quality to the loss function to ensure the generation of de-identified face images with guided quality preservation. The proposed model automatically adjusts the generated image according to the different service quality evaluators, so it is generic and efficient in different service scenarios, even some that have nothing to do with simple visual effects. We take facial expression recognition as an example to present experiments on the dataset CelebA to demonstrate the utility-preservation capabilities of QM-VAE. The experimental data show that QM-VAE has the highest quality retention rate of 86%. Compared with the existing method, QM-VAE generates de-identified face images with significantly improved utility and increases the effect by 6.7%.

/pdf/a-novel-generative-model-for-face-privacy-protection-in-8pvuyftd.pdf

A Novel Generative Model for Face Privacy Protection in Video Surveillance with Utility Maintenance

The mass availability of mobile devices equipped with cameras has lead to increased public privacy concerns in recent years. Face de-identification is a necessary first step towards anonymity preservation, and can be trivially solved by blurring or concealing detected faces. However, such naive privacy protection methods are both ineffective and unsatisfying, producing a visually unpleasant result. In this paper, we tackle face de-identification using Deep Autoencoders, by finetuning the encoder to perform face de-identification. We present various methods to finetune the encoder in both a supervised and unsupervised fashion to preserve facial attributes, while generating new faces which are both visually and quantitatively different from the original ones. Furthermore, we quantify the realism and naturalness of the resulting faces by introducing a diversity metric to measure the distinctiveness of the new faces. Experimental results show that the proposed methods can generate new faces with different person identity labels, while maintaining the facelike nature and diversity of the input face images.

Deep autoencoders for attribute preserving face de-identification

Scene geometry estimation and semantic segmentation using image/video data are two active machine learning/computer vision research topics. Given monocular or stereoscopic 3D images, depicted scene/object geometry in the form of depth maps can be successfully estimated, while modern Deep Neural Network (DNN) architectures can accurately predict semantic masks on an image. In several scenarios, both tasks are required at once, leading to a need for combined semantic 3D world mapping methods. In the wake of modern autonomous systems, DNNs that simultaneously handle both tasks have arisen, exploiting machine/deep learning to save up considerably on computational resources and enhance performance, as these tasks can mutually benefit from each other A great application area is 3D road scene modeling and semantic segmentation, e.g., for an autonomous car to identify and localize in 3D space visible pavement regions (marked as “road”) that are essential for autonomous car driving. Due to the significance of this field, this paper surveys the state-of-the-art DNN-based methods for scene geometry estimation, image semantic segmentation and joint inference of both.

/pdf/neural-vision-based-semantic-3d-world-modeling-1jpvv3a47k.pdf

Neural vision-based semantic 3D world modeling

Semantic image segmentation is an important functionality in various applications, such as robotic vision for autonomous cars, drones, etc. Modern Convolutional Neural Networks (CNNs) process input RGB images and predict per-pixel semantic classes. Depth maps have been successfully utilized to increase accuracy over RGB-only input. They can be used as an additional input channel complementing the RGB image, or they may be estimated by an extra neural branch under a multitask training setting. Contrary to these approaches, in this paper we explore a novel regularizer that penalizes differences between semantic and self-supervised depth predictions on presumed object boundaries during CNN training. The proposed method does not resort to multitask training (which may require a more complex CNN backbone to avoid underfitting), does not rely on RGB-D or stereoscopic 3D training data and does not require known or estimated depth maps during inference. Quantitative evaluation on a public scene parsing video dataset for autonomous driving indicates enhanced semantic segmentation accuracy with zero inference runtime overhead.

Sotirios Papadopoulos

Papers

Deep autoencoders for attribute preserving face de-identification

Neural vision-based semantic 3D world modeling

Semantic Image Segmentation Guided By Scene Geometry