Adversarial Parametric Pose Prior

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

Atomistic simulations performed with a family of model potential with tunable hardness have proven to be a great tool for advancing the understanding of wear processes at the asperity level. They have been instrumental in finding a critical length scale, w ...

The shapes of galaxies, their outer regions in particular, are important guideposts to their formation and evolution. In this work, we report on the discovery of strongly box-shaped morphologies of the otherwise well-studied elliptical and lenticular galax ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

One major challenge in distributed learning is to efficiently learn for each client when the data across clients is heterogeneous or non iid (not independent or identically distributed). This provides a significant challenge as the data of the other client ...

Two related methods for inverting line-integrated measurements are presented in this research paper in the context of the recent deuterium-tritium experiments in the JET tokamak. Unlike traditional methods of tomography, these methods rely on making use of ...

Interactions are ubiquitous in our world, spanning from social interactions between human individuals to physical interactions between robots and objects to mechanistic interactions among different components of an intelligent system. Despite their prevale ...

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to ...

One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially-chosen perturbations of data. Despite the promi ...

We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photo-like images of fullbody humans with consistent appearances under different view-angles and body-poses. To tackle the representational and computational challenges in sy ...

According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...

Metal-based Laser Powder Bed Fusion (LPBF) has made fabricating intricate components easier. Yet, assessing part quality is inefficient, relying on costly Computed Tomography (CT) scans or time-consuming destructive tests. Also, intermittent inspection of ...

Laser Powder Bed Fusion (LPBF) is an Additive Manufacturing (AM) process consolidating parts layer by layer, from a metallic powder bed. It allows no limitation in terms of geometry and is therefore of particular interest to various industries. Metallic LP ...

Machine learning (ML) applications are ubiquitous. They run in different environments such as datacenters, the cloud, and even on edge devices. Despite where they run, distributing ML training seems the only way to attain scalable, high-quality learning. B ...

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard accuracy and com ...

Humans can rapidly estimate the statistical properties of groups of stimuli, including their average and variability. But recent studies of so-called Feature Distribution Learning (FDL) have shown that observers can quickly learn even more complex aspects ...

Image noise can often be accurately fitted to a Poisson-Gaussian distribution. However, estimating the distribution parameters from a noisy image only is a challenging task. Here, we study the case when paired noisy and noise-free samples are accessible. N ...

Many robotics problems are formulated as optimization problems. However, most optimization solvers in robotics are locally optimal and the performance depends a lot on the initial guess. For challenging problems, the solver will often get stuck at poor loc ...

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...

Adversarial Parametric Pose Prior

Chat with Graph Search

Generalization of Scaled Deep ResNets in the Mean-Field Regime

A story of two transitions: From adhesive to abrasive wear and from ductile to brittle regime

The Halos and Environments of Nearby Galaxies (HERON) survey IV. Complexity in the boxy galaxies NGC720 and NGC2768

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Personalized Privacy-Preserving Distributed Learning on Heterogeneous Data

Regressive Tomography and Direct Regressive Reconstruction: A Research Note

Learning Robust and Adaptive Representations: from Interactions, for Interactions

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Fast Adversarial Training With Adaptive Step Size

Adversarial Training Should Be Cast As a Non-Zero-Sum Game

3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping

Robust Training and Verification of Deep Neural Networks

Optimizing in-situ monitoring for laser powder bed fusion process: Deciphering acoustic emission and sensor sensitivity with explainable machine learning

Towards Robust Monitoring of the Laser Powder Bed Fusion Process based on Acoustic Emission combined with Machine Learning Solutions

System Support for Robust Distributed Learning

Towards Robust Vision Transformer

Feature distribution learning by passive exposure

PoGaIN: Poisson-Gaussian Image Noise Modeling From Paired Samples

Memory of Motion for Initializing Optimization in Robotics

Robustness and invariance properties of image classifiers