Publication

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

Related publications (30)

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Devis Tuia, Valérie Zermatten, Javiera Francisca Castillo Navarro, Xiaolong Lu

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

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

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

The multimodality cell segmentation challenge: toward universal solutions

Xin Yang, Bo Wang, Yixin Wang, Jun Ma, Lin Han, Maxime Emmanuel Scheder, Marco Labagnara, Sahand Jamal Rahi, Vojislav Gligorovski, Yao Zhang

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 ...

Nature Portfolio2024

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

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

Driving and suppressing the human language network using large language models

Martin Schrimpf

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

Nature Portfolio2024

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Alexander Carl Unnervik

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

EPFL2024

Toward Automatic Typography Analysis: Serif Classification and Font Similarities

Mathieu Salzmann, Nicolas Henchoz, Delphine Ribes Lemay, Romain Simon Collaud, Syed Talal Wasim

Whether a document is of historical or contemporary significance, typography plays a crucial role in its composition. From the early days of modern printing, typographic techniques have evolved and transformed, resulting in changes to the features of typog ...

2024

Airborne sensor fusion: Expected accuracy and behavior of a concurrent adjustment

Jan Skaloud, Davide Antonio Cucci, Aurélien Arnaud Brun, Kyriaki Mouzakidou

Tightly-coupled sensor orientation, i.e. the simultaneous processing of temporal (GNSS and raw inertial) and spatial (image and lidar) constraints in a common adjustment, has demonstrated significant improvement in the quality of attitude determination wit ...

2024

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

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 ...

EPFL2024

A semantic model-based systems engineering approach for assessing the operational performance of metal forming process

Dimitrios Kyritsis, Jinzhi Lu, Xiaochen Zheng

Metal Forming is a basic and essential industrial process to provide materials for constructing complex products. To design an efficient metal forming process, the functional requirements and operational performance are two important aspects to be consider ...

Pergamon-Elsevier Science Ltd2024

Robust machine learning for neuroscientific inference

Steffen Schneider

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 ...

EPFL2024

Learning Transformations To Reduce the Geometric Shift in Object Detection

Mathieu Salzmann, Martin Pierre Engilberge, Vidit Vidit

The performance of modern object detectors drops when the test distribution differs from the training one. Most of the methods that address this focus on object appearance changes caused by, e.g., different illumination conditions, or gaps between syntheti ...

Ieee Computer Soc2023

Rigidity-Aware Detection for 6D Object Pose Estimation

Mathieu Salzmann, Yinlin Hu, Rui Song, Jingyu Li

Most recent 6D object pose estimation methods first use object detection to obtain 2D bounding boxes before actually regressing the pose. However, the general object detection methods they use are ill-suited to handle cluttered scenes, thus producing poor ...

Ieee Computer Soc2023

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

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

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

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

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

Improving Object Detection under Domain Shifts

Vidit Vidit

Object detection plays a critical role in various computer vision applications, encompassing domains like autonomous vehicles, object tracking, and scene understanding. These applica- tions rely on detectors that generate bounding boxes around known object ...

EPFL2023

Interpretable Representation Learning and Evaluation for Abstractive Summarization

Andreas Thomas Marfurt

Abstractive summarization has seen big improvements in recent years, mostly due to advances in neural language modeling, language model pretraining, and scaling models and datasets. While large language models generate summaries that are fluent, coherent, ...

EPFL2023