Andrei Bursuc

Andrei Bursuc

Auto-generated profile, based on publicly available information

Andrei Bursuc

Valeo.ai

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2019
Verified
Conference Paper
Open access
YLYann Lifchitz
Yann Lifchitz
YAYannis Avrithis
Yannis Avrithis
SPSylvaine Picard
Sylvaine Picard
ABAndrei Bursuc
Andrei Bursuc
Few-shot learning for deep neural networks is a highly challenging and key problem in many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available examples. We propose two simple and effective solutions: (i) dense classification over feature maps, which for the first time studies local activations in the domain of few-shot learning, and (ii) implanting, that is, attaching new neurons to a previously trained network to learn new, task-specific features. Implanting enables training of multiple layers in the few-shot regime, departing from most related methods derived from metric learning that train only the final layer. Both contributions show consistent gains when used individually or jointly and we report state of the art performance on few-shot classification on miniImageNet.

24 November 2024
Verified
Book Chapter
Closed access
PDF file
MWMonika Wysoczańska
Monika Wysoczańska
OSOriane Siméoni
Oriane Siméoni
MRMichaël Ramamonjisoa
Michaël Ramamonjisoa
ABAndrei Bursuc
Andrei Bursuc
Tomasz TrzcinskiTomasz Trzcinski
Tomasz Trzcinski
PPPatrick Pérez
Patrick Pérez

19 November 2020
Verified
Book Chapter
Closed access
PDF file
GFGianni Franchi
Gianni Franchi
ABAndrei Bursuc
Andrei Bursuc
EAEmanuel Aldea
Emanuel Aldea
SDSéverine Dubuisson
Séverine Dubuisson
IBIsabelle Bloch
Isabelle Bloch

31 October 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
GFGianni Franchi
Gianni Franchi
ABAndrei Bursuc
Andrei Bursuc
EAEmanuel Aldea
Emanuel Aldea
SDSéverine Dubuisson
Séverine Dubuisson
IBIsabelle Bloch
Isabelle Bloch
Bayesian Neural Networks (BNNs) have long been considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks. While they could capture more accurately the posterior distribution of the network parameters, most BNN approaches are either limited to small networks or rely on constraining assumptions, e.g., parameter independence. These drawbacks have enabled prominence of simple, but computationally heavy approaches such as Deep Ensembles, whose training and testing costs increase linearly with the number of networks. In this work we aim for efficient deep BNNs amenable to complex computer vision architectures, e.g., ResNet-50 DeepLabv3+, and tasks, e.g., semantic segmentation and image classification, with fewer assumptions on the parameters. We achieve this by leveraging variational autoencoders (VAEs) to learn the interaction and the latent distribution of the parameters at each network layer. Our approach, called Latent-Posterior BNN (LP-BNN), is compatible with the recent BatchEnsemble method, leading to highly efficient (in terms of computation and memory during both training and testing) ensembles. LP-BNNs attain competitive results across multiple metrics in several challenging benchmarks for image classification, semantic segmentation, and out-of-distribution detection.

23 October 2022
Verified
Book Chapter
Closed access
PDF file
AVAntonin Vobecky
Antonin Vobecky
DHDavid Hurych
David Hurych
OSOriane Siméoni
Oriane Siméoni
SGSpyros Gidaris
Spyros Gidaris
ABAndrei Bursuc
Andrei Bursuc
JSJosef Sivic
Josef Sivic

3 November 2022
Verified
Book Chapter
Closed access
PDF file
HVHuy V. Vo
Huy V. Vo
OSOriane Siméoni
Oriane Siméoni
SGSpyros Gidaris
Spyros Gidaris
ABAndrei Bursuc
Andrei Bursuc
PPPatrick Pérez
Patrick Pérez
JPJean Ponce
Jean Ponce