Learning the structure of image collections with latent aspect models

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.

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 ...

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 ...

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

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 ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

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 ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

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 ...

Neurodegenerative and neuroinflammatory disorders often involve complex pathophysiological mechanisms that are â to this date â only partially understood. A more comprehensive understanding of those microstructural processes and their characterization ...

Adversarial examples crafted in black-box scenarios are affected by unrealistic colors or spatial artifacts. To prevent these shortcomings, we propose a novel strategy that generates adversarial images with low detectability and high transferability. The p ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either in the form of a ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

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 ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

A robust anomaly detection mechanism should possess the capability to effectively remediate anomalies, restoring them to a healthy state, while preserving essential healthy information. Despite the efficacy of existing generative models in learning the und ...

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 ...

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 ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning (ML) applied to chemistry, we demonstrate the relev ...

Learning the structure of image collections with latent aspect models

Chat with Graph Search

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

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

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Automated Generation of Emotion-Conveying Sounds for Robots

Incorporating Projective Geometry into Deep Learning

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

Robust machine learning for neuroscientific inference

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

Development and clinical validation of computational imaging biomarkers for neurodegenerative diseases

GLoFool: Global Enhancements and Local Perturbations to Craft Adversarial Images

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Deep Active Latent Surfaces for Medical Geometries

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

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

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Self-Supervised Anomaly Segmentation via Diffusion Models with Dynamic Transformer UNet

The multimodality cell segmentation challenge: toward universal solutions

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

Towards Trustworthy Deep Learning for Image Reconstruction

Integer Linear Programming for Unsupervised Training Set Selection in Molecular Machine Learning