Enhancing subwavelength image recognition with resonant metamaterial lenses

Romain Christophe Rémy Fleury, Bakhtiyar Orazbayev
2019
Discussion par affiche

Résumé

In this work, we discuss our recent research advances in the field of subwavelength image recognition using deep learning tools. We show that combining locally-resonant metamaterial lenses with a deep learning technique that uses a multi-layered artiﬁcial neural network allows for direct recognition of subwavelength objects from an observer in the far-field, without complex calibration procedures. We will discuss the physics of deeply subwavelength image recognition, and the possibility to tailor the metamaterial lens to increase the conversion of evanescent fields to propagating fields that can reach the far field enhance the image recognition to 80% accuracy for objects as small as λ/10.

Official source

https://infoscience.epfl.ch/record/265920?ln=fr

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Concepts associés

Chargement

Publications associées

Chargement

A Geometry-Inspired Decision-Based Attack

Pascal Frossard, Yujia Liu, Seyed Mohsen Moosavi Dezfooli

Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by querying the model in black-box settings, where no information about the model is released except its final decision. Such decision-based attacks usually require lots of queries, while real-world image recognition systems might actually restrict the number of queries. In this paper, we propose qFool, a novel decision-based attack algorithm that can generate adversarial examples using a small number of queries. The qFool method can drastically reduce the number of queries compared to previous decision-based attacks while reaching the same quality of adversarial examples. We also enhance our method by constraining adversarial perturbations in low-frequency subspace, which can make qFool even more computationally efficient. Altogether, we manage to fool commercial image recognition systems with a small number of queries, which demonstrates the actual effectiveness of our new algorithm in practice.

IEEE COMPUTER SOC2019

Chargement

Far-Field Subwavelength Acoustic Imaging by Deep Learning

Romain Christophe Rémy Fleury, Bakhtiyar Orazbayev

Seeing and recognizing an object whose size is much smaller than the illumination wavelength is a challenging task for an observer placed in the far field, due to the diffraction limit. Recent advances in near- and far-field microscopy have offered several ways to overcome this limitation; however, they often use invasive markers and require intricate equipment with complicated image postprocessing. On the other hand, a simple marker-free solution for high-resolution imaging may be found by exploiting resonant metamaterial lenses that can convert the subwavelength image information contained in the near field of the object to propagating field components that can reach the far field. Unfortunately, resonant metalenses are inevitably sensitive to absorption losses, which has so far largely hindered their practical applications. Here, we solve this vexing problem and show that this limitation can be turned into an advantage when metalenses are combined with deep learning techniques. We demonstrate that combining deep learning with lossy metalenses allows recognizing and imaging largely subwavelength features directly from the far field. Our acoustic learning experiment shows that, despite being 30 times smaller than the wavelength of sound, the fine details of images can be successfully reconstructed and recognized in the far field, which is crucially favored by the presence of absorption. We envision applications in acoustic image analysis, feature detection, object classification, or as a novel noninvasive acoustic sensing tool in biomedical applications.

2020

Chargement

Deep Neural Networks (DNNs) have achieved great success in a wide range of applications, such as image recognition, object detection, and semantic segmentation. Even thoughthe discriminative power of DNNs is nowadays unquestionable, serious concerns have arised ever since DNNs have shown to be vulnerable to adversarial examples craftedby adding imperceptible perturbations to clean images. The implications of these malicious attacks are even more significant for DNNs deployed in real-world systems, e.g.,autonomous driving and biometric authentication. Consequently, an intriguing question that we aim to understand is the underlying behavior of DNNs to adversarial attacks.This thesis contributes to a better understanding of the mechanism of adversarial attacks on DNNs. Our main contributions are broadly in two directions: (1) we proposeinterpretable architectures first to understand the reasons for the success of adversarial attacks and then to improve the robustness of DNNs; (2) we design intuitive adversarialattacks to both mislead and use as a tool to expand our present understanding of DNNs' internal workings and their limitations. In the first direction, we introduce deep architectures that allow humans to interpret the reasoning process of DNNs prediction. Specifically, we incorporate Bag-of-visual-wordsrepresentations from the pre-deep learning era into DNNs using an attention scheme. We find key reasons for adversarial attack success and use these insights to propose anadversarial defense by maximally separating the latent features of discriminative regions while minimizing the contribution of non-discriminative regions in the final prediction.The second direction deals with the design of adversarial attacks to understand DNNs' limitations in a real-world environment. To begin with, we show that existing state-of-the-art semantic segmentation networks that achieve superior performance by exploiting the context are highly susceptible to indirect local attacks. Furthermore, we demonstrate the existence of universal directional perturbations that are quasi-independent of the input template but still successfully fool unknown siamese-based visual object trackers. We then identify that the mid-level filter banks across different backbones bear strong similarities and thus can be potential common ground for attack. We, therefore, learn a generator that disrupts mid-level features with high transferability across different target architectures, datasets, and tasks. In short, our attacks highlight critical vulnerabilities of DNNs, which make their deployment challenging in the real-world environment, even in the extreme case when the attacker is unaware of the target architecture or the targetdata used to train it.Furthermore, we go beyond fooling networks and demonstrate the usefulness of adversarial attacks for studying the internal disentangled representations in self-supervised 3D pose estimation networks. We observe that adversarial manipulation of appearance information in the input image alters the pose output, indicating that the pose code contains appearance information and disentanglement is far from complete. Besides the above contributions, an underlying theme that arises multiple times in this thesis is counteracting the adversarial attacks by detecting them.

EPFL2022

Chargement

EPFL2022