Object Detection with Active Sample Harvesting

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 manuscript is the lecture notes of B. Barak’s course in the Les Houches ‘Statistical Physics and Machine Learning’ summer school in 2022. It surveys various proxies for computational hardness in random planted problems, from the low-degree likelihood ...

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 ...

Non-Bayesian social learning is a framework for distributed hypothesis testing aimed at learning the true state of the environment. Traditionally, the agents are assumed to receive observations conditioned on the same true state, although it is also possib ...

The reported rate of the occurrence of unilateral spatial neglect (USN) is highly variable likely due to the lack of validity and low sensitivity of classical tools used to assess it. Virtual reality (VR) assessments try to overcome these limitations by pr ...

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 ...

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 ...

Metabolic changes precede malignant histology. However, it remains unclear whether detectable characteristic metabolome exists in esophageal squamous cell carcinoma (ESCC) tissues and biofluids for early diagnosis. Here, we conduct NMR- and MS-based metabo ...

Machine learning has provided a means to accelerate early-stage drug discovery by combining molecule generation and filtering steps in a single architecture that leverages the experience and design preferences of medicinal chemists. However, designing mach ...

The COVID-19 pandemic has led to a significant increase in working from home worldwide, making the workfrom-home (WFH) setting a crucial context for studying the influence of indoor environmental quality (IEQ) on workers' well-being and productivity. A nar ...

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 ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

Domain generalization (DG) aims to learn a model from multiple training (i.e., source) domains that can generalize well to the unseen test (i.e., target) data coming from a different distribution. Single domain generalization (SingleDG) has recently emerge ...

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 ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object detection remai ...

A large variety of new physics models suggest that the rates for lepton flavour violating

b

-hadron decays may be much higher than predicted in the Standard Model, which leads to a high interest in the search for such decays. This thesis presents the se ...

Deep-learning-based digital twins (DDT) are a promising tool for data-driven system health management because they can be trained directly on operational data. A major challenge for efficient training however is that industrial datasets remain unlabeled. T ...

Object Detection with Active Sample Harvesting

Chat with Graph Search

Computational complexity of deep learning: fundamental limitations and empirical phenomena

Robust machine learning for neuroscientific inference

Detection of Malicious Agents in Social Learning

An immersive virtual reality tool for assessing left and right unilateral spatial neglect

Meta-learning to address diverse Earth observation problems across resolutions

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

NMR and MS reveal characteristic metabolome atlas and optimize esophageal squamous cell carcinoma early detection

Machine learning-aided generative molecular design

A state-of-the-art, systematic review of indoor environmental quality studies in work-from-home settings

Understanding generalization and robustness in modern deep learning

Extensions of Peer Prediction Incentive Mechanisms

Center-aware Adversarial Augmentation for Single Domain Generalization

Incorporating Projective Geometry into Deep Learning

Random matrix methods for high-dimensional machine learning models

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

Search for the lepton flavour violating decays B0→e±μ∓ and B0s→e±μ∓ with LHCb Run 2 data

A Study on Gradient-based Meta-learning for Robust Deep Digital Twins