Publication

Learning to Find Unpaired Cross-Spectral Correspondences

Publications associées (30)

Attribute Prediction as Multiple Instance Learning

Attribute-based representations help machine learning models perform tasks based on human understandable concepts, allowing a closer human-machine collaboration. However, learning attributes that accurately reflect the content of an image is not always str ...

2022

Natural-Looking Adversarial Examples From Freehand Sketches

Davide Nanni, Hakgu Kim

Deep neural networks (DNNs) have achieved great success in image classification and recognition compared to previous methods. However, recent works have reported that DNNs are very vulnerable to adversarial examples that are intentionally generated to misl ...

IEEE2022

Improving the Training of Compact Neural Networks for Visual Recognition

Shuxuan Guo

During the Artificial Intelligence (AI) revolution of the past decades, deep neural networks have been widely used and have achieved tremendous success in visual recognition. Unfortunately, deploying deep models is challenging because of their huge model s ...

EPFL2022

Learning to Represent and Reconstruct 3D Deformable Objects

Jan Bednarík

Representing and reconstructing 3D deformable shapes are two tightly linked problems that have long been studied within the computer vision field. Deformable shapes are truly ubiquitous in the real world, whether be it specific object classes such as human ...

EPFL2022

Weakly Supervised Volumetric Image Segmentation with Deformed Templates

Pascal Fua, Pamuditha Udaranga Wickramasinghe, Patrick Moller Jensen, Mian Akbar Shah

There are many approaches to weakly-supervised training of networks to segment 2D images. By contrast, existing approaches to segmenting volumetric images rely on full-supervision of a subset of 2D slices of the 3D volume. We propose an approach to volume ...

Springer2022

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Apostolos Modas, Guillermo Ortiz Jimenez

Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability, prior works have built complex data augmentation strategies, combining multi ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

reference data for "A Critical Comparison of Annual Glare Simulation Methods"

Jan Wienold, Stephen William Wasilewski

Scene and reference results files for: "A Critical Comparison of Annual Glare Simulation Methods" Stephen Wasilewski, Jan Wienold, Marilyne Andersen 2022 Buildsim Nordic, Copenhagen Contents: 01-06*.tar.gz: reference simulation image archives, one ...

Zenodo2022

MultiMAE: Multi-modal Multi-task Masked Autoencoders

Amir Roshan Zamir, Roman Christian Bachmann, David Mizrahi, Andrei Atanov

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

Object Priors for Volumetric Image Segmentation

Pamuditha Udaranga Wickramasinghe

Large training datasets have played a vital role in the success of modern deep learning methods in computer vision. But, obtaining sufficient amount of training data is challenging, specially when annotating volumetric images. This is because fully annotat ...

EPFL2022

Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation

Jean-Philippe Thiran, Manana Lortkipanidze, Guillaume Marc Georges Vray, Seyedbehzad Bozorgtabar, Devavrat Tomar

Despite the successes of deep neural networks on many challenging vision tasks, they often fail to generalize to new test domains that are not distributed identically to the training data. The domain adaptation becomes more challenging for cross-modality m ...

Institute of Electrical and Electronics Engineers2021