Weighting Schemes for Federated Learning in Heterogeneous and Imbalanced Segmentation Datasets

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.

Given a ground-level query image and a geo-referenced aerial image that covers the query’s local surroundings, fine-grained cross-view localization aims to estimate the location of the ground camera inside the aerial image. Recent works have focused on dev ...

The digitization of 3D deformable objects remains a significant challenge in computer graphics and vision, particularly in the accurate modeling of garments. Garments exhibit complex shape variability, non-rigid deformations, and frequent self-occlusion, m ...

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition (ASR) on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are train ...

To retrieve Surface Solar Radiation (SSR) from satellite images, a baseline reflectance of the observed ground in clear-sky conditions, also called background reflectance, is necessary to distinguish atmospheric absorption and scattering effects from surfa ...

Estimating ecosystem-atmosphere fluxes such as evapotranspiration (ET) in a robust manner and at a global scale remains a challenge. Methods based on machine learning (ML) have shown promising results in achieving such upscaling, providing a complementary ...

Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcrib ...

Object detection, a fundamental task in computer vision, is crucial for various intelligent edge computing applications. However, object detection algorithms are usually heavy in computation, hindering their deployments on resource-constrained edge devices ...

Sonic Human-Robot Interaction aims at equipping robots with the ability to convey emotions and intentions via sounds. Such sounds are typically handcrafted by human experts, which results in expensive, small sound sets with limited expressivity. To overcom ...

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high ...

Machine learning is increasingly integrated with decision making by powering automated systems and informing human decision makers in applications such as CV screening, portfolio allocation, loan risk assessment, and insurance approval. In this thesis, I e ...

Photorealistic synthetic data and novel rendering techniques significantly advanced computer vision research. However, datasets focused on computer vision applications cannot be easily applied to robotics because they typically lack physics-related informa ...

Developing agents that can reliably act on our behalf is central to artificial intelligence (AI). These agents must seamlessly interact with tools, like search engines and databases, and collaborate. In this thesis, we study the abstractions, methods, and ...

The field of text-to-video retrieval has advanced significantly with the evolution of language models and large-scale pre-training on generated caption-video pairs. Current methods predominantly focus on visual and event-based details, making retrieval lar ...

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly impacting their ...

The widespread application of machine learning (ML) to the chemical sciences is making it very important to understand how the ML models learn to correlate chemical structures with their properties, and what can be done to improve the training efficiency w ...

Smart meters, devices measuring the electricity and gas consumption of a household, are currently being deployed at a fast rate throughout the world. The data they collect are extremely useful, including in the fight against climate change. However, these ...

Utilization of small molecules as passivation materials for perovskite solar cells (PSCs) has gained significant attention recently, with hundreds of small molecules demonstrating passivation effects. In this study, a high-accuracy machine learning model i ...

In this paper, we present EdgeFace - a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achi ...

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional data representatio ...

Weighting Schemes for Federated Learning in Heterogeneous and Imbalanced Segmentation Datasets

Chat with Graph Search

Adapting Fine-Grained Cross-View Localization to Areas Without Fine Ground Truth

Neural Garment Modeling

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

Retrieval of Surface Solar Radiation through Implicit Albedo Recovery from Temporal Context

On the added value of sequential deep learning for the upscaling of evapotranspiration

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR

Edge-Cloud Collaborated Object Detection via Bandwidth Adaptive Difficult-Case Discriminator

Automated Generation of Emotion-Conveying Sounds for Robots

Enhancing skin lesion classification: a CNN approach with human baseline comparison

Machine Learning in Decision-Making Systems: Fairness, Robustness, and Data Bias

GRADE: Generating Realistic and Dynamic Environments for robotics research with Isaac Sim

Collaborative AI Agents in the Era of Large Language Models

Beyond Essentials: Nuanced and Diverse Text-to-video Retrieval

Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers

Prediction rigidities for data-driven chemistry

Re-pseudonymization Strategies for Smart Meter Data Are Not Robust to Deep Learning Profiling Attacks

Machine Learning for Screening Small Molecules as Passivation Materials for Enhanced Perovskite Solar Cells

EdgeFace: Efficient Face Recognition Model for Edge Devices

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model