DSS: Synthesizing Long Digital Ink Using Data Augmentation, Style Encoding and Split Generation

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.

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce. Likewise, accessin ...

Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and req ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data's inherent structure or context by solving a pretext task. With ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Federated learning (FL) has recently emerged as a compelling machine learning paradigm, prioritizing the protection of privacy for training data. The increasing demand to address issues such as "the right to be forgotten" and combat data poisoning attacks ...

Purpose The aim of this study was to develop a novel approach for predicting the expression status of Epidermal Growth Factor Receptor (EGFR) and its subtypes in patients with Non-Small Cell Lung Cancer (NSCLC) using a Three-Dimensional Convolutional Neura ...

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

High PV penetration into the electricity grid can lead to issues such as congestion if PV systems are not integrated effectively. Accurate PV power forecasting helps to address this issue. In recent years machine learning approaches have gotten a lot of at ...

We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such adaptation. Nevertheless, catastrophic forgetting remains an i ...

Accurate real-time prediction of aerodynamic forces is crucial for the navigation of unmanned aerial vehicles (UAVs). This paper presents a data-driven aerodynamic force prediction model based on a small number of pressure sensors located on the surface of ...

Deploying compute-intensive deep neural networks (DNNs) on resource-constrained end devices has become a prominent trend, enabling localized intelligence. However, efficiently deploying these DNNs at scale poses challenges. To address this, extensive resea ...

This paper investigates the potential impact of deep generative models on the work of creative professionals. We argue that current generative modeling tools lack critical features that would make them useful creativity support tools, and introduce our own ...

Species distribution models (SDMs) aim to predict the distribution of species by relating occurrence data with environmental variables. Recent applications of deep learning to SDMs have enabled new avenues, specifically the inclusion of spatial data (envir ...

In this paper, we use synthetic data and propose a new method for template inversion attacks against face recognition systems. We use synthetic data to train a face reconstruction model to generate high-resolution (i.e., 1024 x 1024) face images from facia ...

The rapid progress of industrial development, urbanization, and traffic has caused air quality degradation that negatively affects human health and environmental sustainability, especially in developed countries. However, due to the limited number of senso ...

Emotion recognition through artificial intelligence and smart sensing of physical and physiological signals (affective computing) is achieving very interesting results in terms of accuracy, inference times, and user-independent models. In this sense, there ...

DSS: Synthesizing Long Digital Ink Using Data Augmentation, Style Encoding and Split Generation

Chat with Graph Search

Probing the latent hierarchical structure of data via diffusion models

Self-supervised and few-shot learning for robust bioaerosol monitoring

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

A phase transition between positional and semantic learning in a solvable model of dot-product attention

A Closer Look at Benchmarking Self-supervised Pre-training with Image Classification

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Meta-learning to address diverse Earth observation problems across resolutions

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience

Advancing EGFR mutation subtypes prediction in NSCLC by combining 3D pretrained ConvNeXt, radiomics, and clinical features

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life

Model Tuning and Performance Evaluation in Machine Learning Models for PV Power Forecasting: Case Study of a BIPV System in Switzerland

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting

Machine-Learning-Enhanced Real-Time Aerodynamic Forces Prediction Based on Sparse Pressure Sensor Inputs

RAPNet: Resolution-Adaptive and Predictive Early Exit Network for Efficient Image Recognition

Fashioning Creative Expertise with Generative AI: Graphical Interfaces for GAN-Based Design Space Exploration Beter Support Ideation Than Text Prompts for Difusion Models

Multi-Scale and Multimodal Species Distribution Modeling

Template Inversion Attack Using Synthetic Face Images Against Real Face Recognition Systems

Self-supervised air quality estimation with graph neural network assistance and attention enhancement

Personalized Clustering for Emotion Recognition Improvement