Home

Publication

MultiMAE: Multi-modal Multi-task Masked Autoencoders

About
Privacy
Disclaimer

Graph Chatbot

Related publications (53)

Page 2 of 3

Aggregating Spatial and Photometric Context for Photometric Stereo

David Honzátko

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Evann Pierre Guy Courdier

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 ...

EPFL2024

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Devis Tuia, Valérie Zermatten, Javiera Francisca Castillo Navarro

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 ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Devis Tuia, Lloyd Haydn Hughes, Javiera Francisca Castillo Navarro, Valérie Zermatten

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

The Institute of Electrical and Electronics Engineers, Inc2023

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Seyed Mohammad Mahdi Johari

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 ...

EPFL2024

Detecting Anomalies and Obstacles in Road Scenes

Krzysztof Maciej Lis

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

EPFL2023

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Pascal Fua, Mathieu Salzmann, Andrey Davydov

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Journal of Machine Learning Research Inc.2024

Transformer Models for Vision

Jean-Baptiste Francis Marie Juliette Cordonnier

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 ...

EPFL2023

Segmenting Without Annotating: Crack Segmentation and Monitoring via Post-Hoc Classifier Explanations

Devis Tuia, Olga Fink, Florent Evariste Forest, Hugo Laurent Pascal Porta

Monitoring the cracks in walls, roads and other types of infrastructure is essential to ensure the safety of a structure, and plays an important role in structural health monitoring. Automatic visual inspection allows an efficient, costeffective and safe h ...

Research Publishing2023

Enabling Uncertainty Estimation in Iterative Neural Networks

Pascal Fua, Minh Hieu Lê, Doruk Oner, Nikita Durasov

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

Curran Associates2024

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Mattia Atzeni

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

EPFL2024

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

Mathieu Salzmann, Martin Pierre Engilberge, Vidit Vidit

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 ...

Ieee Computer Soc2023

Asymptotics of feature learning in two-layer networks after one gradient-step

Lenka Zdeborová, Florent Gérard Krzakala, Bruno Loureiro, Hugo Chao Cui, Yatin Dandi, Luca Pesce, Yue Lu

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we model t ...

2024

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations

Leonardo Petrini

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as natural language proc ...

EPFL2023

Stellar Metallicities and Gradients in the Isolated, Quenched Low-mass Galaxy Tucana

Nicolas Lawrence Etienne Longeard

We measure the metallicities of 374 red giant branch (RGB) stars in the isolated, quenched dwarf galaxy Tucana using Hubble Space Telescope (HST) narrow-band (F395N) Calcium H & K (CaHK) imaging. Our sample is a factor of similar to 7 similar to 7 larger t ...

Iop Publishing Ltd2024

Improving Generalization of Pretrained Language Models

Rabeeh Karimi Mahabadi

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

EPFL2023

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis

Mathew Magimai Doss, Eklavya Sarkar

Marmoset monkeys encode vital information in their calls and serve as a surrogate model for neuro-biologists to understand the evolutionary origins of human vocal communication. Traditionally analyzed with signal processing-based features, recent approache ...

2024

Deep Learning Generalization with Limited and Noisy Labels

Mahsa Forouzesh

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

EPFL2023

4M: Massively Multimodal Masked Modeling

David Mizrahi, Amir Roshan Zamir, Shuqing Teresa Yeo, Oguzhan Fatih Kar, Roman Christian Bachmann

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in co ...

Neural Information Processing Systems (Nips)2023