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.

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

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 ...

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 ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

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 ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

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 ...

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

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 ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

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 ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

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 ...

Human motion analysis and synthesis is integral to many computer vision applications, from autonomous driving to sports analysis. In this thesis, we address several problems in this domain. First we consider active viewpoint selection for pose estimation w ...

Objective: Brain-body interfaces (BBIs) have emerged as a very promising solution for restoring voluntary hand control in people with upper-limb paralysis. The BBI module decoding motor commands from brain signals should provide the user with intuitive, ac ...

Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propose an ...

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 ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

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 ...

Learning to Find Good Correspondences

Chat with Graph Search

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Driving and suppressing the human language network using large language models

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

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Understanding generalization and robustness in modern deep learning

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

The multimodality cell segmentation challenge: toward universal solutions

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

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

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

Sparse autoregressive neural networks for classical spin systems

Network time series forecasting in photovoltaics power production

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

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

Automated Human Motion Analysis and Synthesis

An Investigation of Manifold-Based Direct Control for a Brain-to-Body Neural Bypass

An exact mapping from ReLU networks to spiking neural networks

Efficient local linearity regularization to overcome catastrophic overfitting

Supervised learning and inference of spiking neural networks with temporal coding

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms