Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift

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.

Let K be an algebraically closed field of characteristic zero, and let G be a connected reductive algebraic group over K. We address the problem of classifying triples (G, H, V ), where H is a proper connected subgroup of G, and V is a finitedimensional ir ...

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 ...

Because building-integrated photovoltaic (BIPV) modules are fully integrated into a building envelope, the back of the module can be exposed to little or no ventilation, resulting in increased operating temperatures. As the temperature increases, the perfo ...

This study explores the differences in performance and results by various versions of the ISORROPIA thermodynamic module implemented within the ECHAM/MESSy Atmospheric Chemistry (EMAC) model. Three different versions of the module were used, ISORROPIA II v ...

Modular robotics link the reliability of a centralised system with the adaptivity of a decentralised system. It is difficult for a robot with a fixed shape to be able to perform many different types of tasks. As the task space grows, the number of functi ...

Motion forecasting is crucial in enabling autonomous vehicles to anticipate the future trajectories of surrounding agents. To do so, it requires solving mapping, detection, tracking, and then forecasting problems, in a multi-step pipeline. In this complex ...

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 ...

Volume electron microscopy is the method of choice for the in situ interrogation of cellular ultrastructure at the nanometer scale, and with the increase in large raw image datasets generated, improving computational strategies for image segmentation and s ...

A correspondence functor is a functor from the category of finite sets and correspondences to the category of k-modules, where k is a commutative ring. By means of a suitably defined duality, new correspondence functors are constructed, having remarkable p ...

Pulmonary nodules and masses are crucial imaging features in lung cancer screening that require careful management in clinical diagnosis. Despite the success of deep learning-based medical image segmentation, the robust performance on various sizes of lesi ...

In high energy physics, semiconductor-based sensors are widely used in particle tracking applications. These sensors are typically glued on low-mass cooling substrates, which guarantee the correct thermal management and, at the same time, minimise their in ...

Incomplete labels are common in multi-task learning for biomedical applications due to several practical difficulties, e.g., expensive annotation efforts by experts, limit of data collection, different sources of data. A naive approach to enable joint lear ...

Exploiting the recent advancements in artificial intelligence, showcased by ChatGPT and DALL-E, in real-world applications necessitates vast, domain-specific, and publicly accessible datasets. Unfortunately, the scarcity of such datasets poses a significan ...

The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges our unde ...

Regulation of gene expression is a complex but highly guided process. While genomic technologies and computational approaches have allowed high-throughput mapping of cis-regulatory elements (CREs) and their interactions in 3D, their precise role in regulat ...

Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical r ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Models trained with counterfactually augmented data learn representations of the causal structure of tasks, enabling robust generalization. However, high-quality counterfactual data is scarce for most tasks and not easily generated at scale. When crowdsour ...

Author summaryIn recent years, the application of deep learning represented a breakthrough in the mass spectrometry (MS) field by improving the assignment of the correct sequence of amino acids from observable MS spectra without prior knowledge, also known ...

Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, ca ...

Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift

Chat with Graph Search

Multiplicity-free Representations of Algebraic Groups

Robust machine learning for neuroscientific inference

Correlating long-term performance and aging behaviour of building integrated PV modules

Implementation of the ISORROPIA-lite aerosol thermodynamics model into the EMAC chemistry climate model (based on MESSy v2.55): implications for aerosol composition and acidity

Memento Mori: Reliable robustness in self-reconfigurable modular robots

Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?

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

Modular segmentation, spatial analysis and visualization of volume electron microscopy datasets

Correspondence functors and duality

Scale-Aware Test-Time Click Adaptation for Pulmonary Nodule and Mass Segmentation

Interlocking modular microfluidic cooling substrates for future high energy physics experiments

MULTI-TASK CURRICULUM LEARNING FOR PARTIALLY LABELED DATA

Dated: Guidelines for Creating Synthetic Datasets for Engineering Design Applications

Monotonicity Reasoning in the Age of Neural Foundation Models

Chromatin modules and their implication in genomic organization and gene regulation

Contrasting action and posture coding with hierarchical deep neural network models of proprioception

Transformer Models for Vision

DISCO: Distilling Counterfactuals with Large Language Models

Multienzyme deep learning models improve peptide de novo sequencing by mass spectrometry proteomics

Leveraging Unlabeled Data to Track Memorization