Learning to Find Good Correspondences

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.

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that theoretical resul ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

Ultrafast ultrasound imaging achieves high frame rates but results in lower image quality compared to focused acquisitions. Convolutional neural networks (CNNs) have emerged as effective tools for reducing diffraction artifacts and enhancing the quality of ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

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 ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface compared to black- ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

Species distribution modeling is a highly versatile tool for understanding the intricate relationship between environmental conditions and species occurrences. However, the available data often lacks information on confirmed species absence and is limited ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Accurate forecasting of photovoltaic (PV) power production is crucial for the integration of more renewable energy sources into the power grid. PV power production is highly intermittent, due to the stochastic cloud behaviour and cloud dynamics. Previous w ...

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we model t ...

Effective Prognostics and Health Management (PHM) relies on accurate prediction of the Remaining Useful Life (RUL). Data-driven RUL prediction techniques rely heavily on the representativeness of the available time-to-failure trajectories. Therefore, these ...

Learning to Find Good Correspondences

Chat with Graph Search

Efficient local linearity regularization to overcome catastrophic overfitting

High-performance deep spiking neural networks with 0.3 spikes per neuron

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

Enhancement of Ultrafast Ultrasound Images: A Performance Comparison Between CNN Trained with RF or IQ Images

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Driving and suppressing the human language network using large language models

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Robust NAS under adversarial training: benchmark, theory, and beyond

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Safe Deep Neural Networks

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Understanding generalization and robustness in modern deep learning

On the selection and effectiveness of pseudo-absences for species distribution modeling with deep learning

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Network time series forecasting in photovoltaics power production

Asymptotics of feature learning in two-layer networks after one gradient-step

Domain adaptation via alignment of operation profile for Remaining Useful Lifetime prediction