Concept
Modèle de fondation
Publications associées (119)
Continual Test-Time Domain Adaptation
Test-time domain adaptation aims to adapt a source pretrained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems are running in n ...
IEEE COMPUTER SOC2022Prompt–RSVQA: Prompting visual context to a language model for Remote Sensing Visual Question Answering
Devis Tuia, Sylvain Lobry, Christel Marie Tartini-Chappuis, Valérie Zermatten
Remote sensing visual question answering (RQA) was recently proposed with the aim of interfacing natural language and vision to ease the access of information contained in Earth Observation data for a wide audience, which is granted by simple questions in ...
20223D Common Corruptions and Data Augmentation
Shuqing Teresa Yeo, Amir Roshan Zamir, Oguzhan Fatih Kar, Andrei Atanov
We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations is that, unlike e ...
IEEE COMPUTER SOC2022Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift
In many situations, the data one has access to at test time follows a different distribution from the training data. Over the years, this problem has been tackled by closed-set domain adaptation techniques. Recently, open-set domain adaptation has emerged ...
IEEE COMPUTER SOC2022End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management
Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g. reviews and doc ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022DG-Mix: Domain Generalization for Anomalous Sound Detection Based on Self-Supervised Learning
Olga Fink, Ismail Nejjar, Gaëtan Michel Frusque
Detecting anomalies in sound data has recently received significant attention due to the increasing number of implementations of sound condition monitoring solutions for critical assets. In this context, changing operating conditions impose significant dom ...
2022Meta Transfer Learning for Early Success Prediction in MOOCs
Despite the increasing popularity of massive open online courses (MOOCs), many suffer from high dropout and low success rates. Early prediction of student success for targeted intervention is therefore essential to ensure no student is left behind in a cou ...
ACM2022Humans are Poor Few-Shot Classifiers for Sentinel-2 Land Cover
Devis Tuia, Marc Conrad Russwurm
Learning to predict accurately from a few data samples is a central challenge in modern data-hungry machine learning. On natural images, human vision typically outperforms deep learning approaches on few-shot learning. However, we hypothesize that aerial a ...
IEEE2022Efficient Transformer-Based Speech Recognition
Training deep neural network based Automatic Speech Recognition (ASR) models often requires thousands of hours of transcribed data, limiting their use to only a few languages. Moreover, current state-of-the-art acoustic models are based on the Transformer ...
EPFL2022