Search Results for author: Laurent Amsaleg

Found 16 papers, 7 papers with code

Towards Good Practices in Evaluating Transfer Adversarial Attacks

1 code implementation17 Nov 2022 Zhengyu Zhao, Hanwei Zhang, Renjue Li, Ronan Sicre, Laurent Amsaleg, Michael Backes

In this work, we design good practices to address these limitations, and we present the first comprehensive evaluation of transfer attacks, covering 23 representative attacks against 9 defenses on ImageNet.

Intrinsic Dimensionality Estimation within Tight Localities: A Theoretical and Experimental Analysis

1 code implementation29 Sep 2022 Laurent Amsaleg, Oussama Chelly, Michael E. Houle, Ken-ichi Kawarabayashi, Miloš Radovanović, Weeris Treeratanajaru

Accurate estimation of Intrinsic Dimensionality (ID) is of crucial importance in many data mining and machine learning tasks, including dimensionality reduction, outlier detection, similarity search and subspace clustering.

Dimensionality Reduction Outlier Detection

Teach me how to Interpolate a Myriad of Embeddings

no code implementations29 Jun 2022 Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis

Finally, to address inconsistencies due to linear target interpolation, we introduce a self-distillation approach to generate and interpolate synthetic targets.

Data Augmentation

AggNet: Learning to Aggregate Faces for Group Membership Verification

no code implementations17 Jun 2022 Marzieh Gheisari, Javad Amirian, Teddy Furon, Laurent Amsaleg

In some face recognition applications, we are interested to verify whether an individual is a member of a group, without revealing their identity.

Face Recognition

AlignMix: Improving representations by interpolating aligned features

no code implementations29 Sep 2021 Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.

Data Augmentation Representation Learning

It Takes Two to Tango: Mixup for Deep Metric Learning

1 code implementation ICLR 2022 Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, Laurent Amsaleg, Konstantinos Karantzalos, Yannis Avrithis

In this work, we aim to bridge this gap and improve representations using mixup, which is a powerful data augmentation approach interpolating two or more examples and corresponding target labels at a time.

Ranked #8 on Metric Learning on CUB-200-2011 (using extra training data)

Data Augmentation Metric Learning +2

AlignMixup: Improving Representations By Interpolating Aligned Features

2 code implementations CVPR 2022 Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.

Data Augmentation Representation Learning +1

Group Membership Verification with Privacy: Sparse or Dense?

no code implementations24 Feb 2020 Marzieh Gheisari, Teddy Furon, Laurent Amsaleg

Group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member.

Joint Learning of Assignment and Representation for Biometric Group Membership

no code implementations24 Feb 2020 Marzieh Gheisari, Teddy Furon, Laurent Amsaleg

This paper proposes a framework for group membership protocols preventing the curious but honest server from reconstructing the enrolled biometric signatures and inferring the identity of querying clients.

Walking on the Edge: Fast, Low-Distortion Adversarial Examples

1 code implementation4 Dec 2019 Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input.

\'Evaluation objective de plongements pour la synth\`ese de parole guid\'ee par r\'eseaux de neurones (Objective evaluation of embeddings for speech synthesis guided by neural networks)

no code implementations JEPTALNRECITAL 2019 Antoine Perquin, Gw{\'e}nol{\'e} Lecorv{\'e}, Damien Lolive, Laurent Amsaleg

La qualit{\'e} des plongements est li{\'e}e {\`a} la t{\^a}che sp{\'e}cifique pour laquelle ils ont {\'e}t{\'e} entra{\^\i}n{\'e}s et l{'}{\'e}valuation de cette t{\^a}che peut {\^e}tre un proc{\'e}d{\'e} long et on{\'e}reux s{'}il y a besoin d{'}annotateurs humains.

Speech Synthesis

Privacy Preserving Group Membership Verification and Identification

no code implementations23 Apr 2019 Marzieh Gheisari, Teddy Furon, Laurent Amsaleg

When convoking privacy, group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member.

Face Recognition Privacy Preserving

Smooth Adversarial Examples

1 code implementation28 Mar 2019 Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg

This paper investigates the visual quality of the adversarial examples.

Dynamicity and Durability in Scalable Visual Instance Search

no code implementations25 May 2018 Herwig Lejsek, Björn Þór Jónsson, Laurent Amsaleg, Friðrik Heiðar Ásmundsson

Systems designed for visual instance search face the major challenge of scalability: a collection of a few million images used for instance search typically creates a few billion features that must be indexed.

Databases Multimedia

Cannot find the paper you are looking for? You can Submit a new open access paper.