Publications related to Indirect Local Attacks for Context-aware Semantic Segmentation Networks

Related publications (21)

High-resolution predictions of the coolant properties for the 3D PWR core with artificial neural networks based on CTF

PSI and North Carolina State University are developing a high-resolution multi-physics core solver for Pressurized Water Reactor (PWR) analysis in Cartesian geometry, using the neutron transport code nTRACER and two Machine Learning (ML) models providing t ...

2025

Differences in Visual Perception in Humans and Deep Neural Networks

Ben Henrik Lönnqvist

Visual grouping is the ability to combine parts of objects to form whole objects, and it is crucial for general and robust vision. Despite this, a comprehensive model of how the process works in humans remains elusive. In my thesis, I investigate how well ...

EPFL2025

Drone-Based Urban Traffic Monitoring and User Behavior Prediction

Sohyeong Kim

As urban populations continue to expand and vehicle density increases, the need for effective traffic monitoring and management becomes increasingly critical. Urban areas face significant challenges such as growing congestion, safety concerns, and parking ...

EPFL2025

Causality: fundamental principles and tools

Elise Hélène Dumas

This chapter aims to provide a gentle introduction to Causal Learning (CL), and motivation for its application to medical image analysis, seeking for more robustness against data and domain drifts, and a reliable tool to answer counterfactual questions and ...

Academic Press2025

Unified Human Localization and Trajectory Prediction with Monocular Vision

Alexandre Massoud Alahi, Yang Gao, Po-Chien Luan

Conventional human trajectory prediction models rely on clean curated data, requiring specialized equipment or manual labeling, which is often impractical for robotic applications. The existing predictors tend to overfit to clean observation affecting thei ...

IEEE2025

Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-training Strategies and Performance Insights

Olga Fink, Florent Evariste Forest

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research has proposed vario ...

Springer Science and Business Media Deutschland GmbH2025

Hierarchical Training of Deep Neural Networks Using Early Exiting

Pascal Frossard, Liza Carol Andrea Dunbar, Ahmet Caner Yüzügüler, Yamin Sepehri

Deep neural networks (DNNs) provide state-of-the-art accuracy for vision tasks, but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases communication ...

Ieee-Inst Electrical Electronics Engineers Inc2024

A Joint Graph Signal and Laplacian Denoising Network

Zepeng Zhang

Graph neural network (GNN) models have presented astonishing achievements in various application fields. However, they are shown to be vulnerable to adversarial attacks on graph structure and unnoticeable perturbations on the graph structure can cause sign ...

Institute of Electrical and Electronics Engineers Inc.2024

Programming nonlinear propagation for efficient optical learning machines

Demetri Psaltis, Christophe Moser, Niyazi Ulas Dinç, Ugur Tegin, Ilker Oguz, Mustafa Yildirim, Carlo Gigli, Jih-Liang Hsieh

The ever-increasing demand for training and inferring with larger machine-learning models requires more efficient hardware solutions due to limitations such as power dissipation and scalability. Optics is a promising contender for providing lower power com ...

Spie-Soc Photo-Optical Instrumentation Engineers2024

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs

Florent Gérard Krzakala, Bruno Loureiro, Ludovic Théo Stephan, Yatin Dandi, Luca Pesce, Luca Arnaboldi

We study the impact of the batch

n_b

on the iteration time

T

of training two-layer neural networks with one-pass stochastic gradient descent (SGD) on multi-index target functions of isotropic covariates. We characterize the optimal batch size minimizin ...

JMLR2024

∇2DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

Egor Rumiantsev

Methods of computational quantum chemistry provide accurate approximations of molecular properties crucial for computer-aided drug discovery and other areas of chemical science. However, high computational complexity limits the scalability of their applica ...

Neural information processing systems foundation2024

AmadeusGPT: a natural language interface for interactive animal behavioral analysis

Alexander Mathis, Mackenzie Mathis, Shaokai Ye, Jessy Lauer, Mu Zhou

The process of quantifying and analyzing animal behavior involves translating the naturally occurring descriptive language of their actions into machine-readable code. Yet, codifying behavior analysis is often challenging without deep understanding of anim ...

2023

Forward-forward training of an optical neural network

Demetri Psaltis, Christophe Moser, Niyazi Ulas Dinç, Ilker Oguz, Mustafa Yildirim, Jih-Liang Hsieh

Neural networks (NNs) have demonstrated remarkable capabilities in various tasks, but their computation-intensive nature demands faster and more energy-efficient hardware implementations. Optics-based platforms, using technologies such as silicon photonics ...

Optica Publishing Group2023

Scale-out Systolic Arrays

Pascal Frossard, Babak Falsafi, Ahmet Caner Yüzügüler, Canberk Sönmez

Multi-pod systolic arrays are emerging as the architecture of choice in DNN inference accelerators. Despite their potential, designing multi-pod systolic arrays to maximize effective throughput/Watt-i.e., throughput/Watt adjusted when accounting for array ...

ASSOC COMPUTING MACHINERY2023

Stochastic Approximation of Variational Quantum Imaginary Time Evolution

Giuseppe Carleo

The imaginary-time evolution of quantum states is integral to various fields, ranging from natural sciences to classical optimization or machine learning. Since simulating quantum imaginary-time evolution generally requires storing an exponentially large w ...

Institute of Electrical and Electronics Engineers Inc.2023

High-speed identification of suspended carbon nanotubes using Raman spectroscopy and deep learning

Martin Jaggi, Luis Felipe Barba Flores

The identification of nanomaterials with the properties required for energy-efficient electronic systems is usually a tedious human task. A workflow to rapidly localize and characterize nanomaterials at the various stages of their integration into large-sc ...

SPRINGERNATURE2022

Chronic recording of cortical activit y underlying vocalization in awake minipigs

Stéphanie Lacour, Giuseppe Schiavone, Florian Dylan Fallegger

Background: Investigating brain dynamics underlying vocal production in animals is a powerf u l w a y to inform on the neural bases of human speech. In particular, brain networks underlying vocal production in non-human primates show striking similarities ...

ELSEVIER2022

Attention is not all you need: pure attention loses rank doubly exponentially with depth

Andreas Loukas, Jean-Baptiste Francis Marie Juliette Cordonnier

Attention-based architectures have become ubiquitous in machine learning. Yet, our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their output can be de ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021

Model-Agnostic Learning to Meta-Learn

Yatin Dandi, Arnout Jan J Devos

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate how learning wi ...

PMLR2021

Capsule networks explain complex spatial processing

Michael Herzog, Adrien Christophe Doerig

Classically, visual processing is described as a cascade of local feedforward computations. This view has received striking support from the success of convolutional neural networks (CNNs). However, CNNs only roughly mimic human vision. For example, CNNs d ...

SAGE PUBLICATIONS LTD2019