Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Cardinaux, Fabien"'
Autor:
Nguyen, Bac, Uhlich, Stefan, Cardinaux, Fabien, Mauch, Lukas, Edraki, Marzieh, Courville, Aaron
Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated remarkable zero-s
Externí odkaz:
http://arxiv.org/abs/2407.03036
Autor:
Bendou, Yassir, Lioi, Giulia, Pasdeloup, Bastien, Mauch, Lukas, Hacene, Ghouthi Boukli, Cardinaux, Fabien, Gripon, Vincent
We consider the problem of zero-shot one-class visual classification, extending traditional one-class classification to scenarios where only the label of the target class is available. This method aims to discriminate between positive and negative qu
Externí odkaz:
http://arxiv.org/abs/2404.00675
Autor:
Bensaid, Reda, Gripon, Vincent, Leduc-Primeau, François, Mauch, Lukas, Hacene, Ghouthi Boukli, Cardinaux, Fabien
In recent years, the rapid evolution of computer vision has seen the emergence of various foundation models, each tailored to specific data types and tasks. In this study, we explore the adaptation of these models for few-shot semantic segmentation.
Externí odkaz:
http://arxiv.org/abs/2401.11311
Autor:
Bendou, Yassir, Gripon, Vincent, Pasdeloup, Bastien, Lioi, Giulia, Mauch, Lukas, Cardinaux, Fabien, Hacene, Ghouthi Boukli
In the realm of few-shot learning, foundation models like CLIP have proven effective but exhibit limitations in cross-domain robustness especially in few-shot settings. Recent works add text as an extra modality to enhance the performance of these mo
Externí odkaz:
http://arxiv.org/abs/2311.14544
Computing gradients of an expectation with respect to the distributional parameters of a discrete distribution is a problem arising in many fields of science and engineering. Typically, this problem is tackled using Reinforce, which frames the proble
Externí odkaz:
http://arxiv.org/abs/2309.03974
State-of-the-art non-autoregressive text-to-speech (TTS) models based on FastSpeech 2 can efficiently synthesise high-fidelity and natural speech. For expressive speech datasets however, we observe characteristic audio distortions. We demonstrate tha
Externí odkaz:
http://arxiv.org/abs/2306.01442
Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its success, this
Externí odkaz:
http://arxiv.org/abs/2303.03717
Autor:
Bendou, Yassir, Gripon, Vincent, Pasdeloup, Bastien, Mauch, Lukas, Uhlich, Stefan, Cardinaux, Fabien, Hacene, Ghouthi Boukli, Garcia, Javier Alonso
The estimation of the generalization error of classifiers often relies on a validation set. Such a set is hardly available in few-shot learning scenarios, a highly disregarded shortcoming in the field. In these scenarios, it is common to rely on feat
Externí odkaz:
http://arxiv.org/abs/2212.06461
Autor:
Jiang, Xiaowen, Cambareri, Valerio, Agresti, Gianluca, Ugwu, Cynthia Ifeyinwa, Simonetto, Adriano, Cardinaux, Fabien, Zanuttigh, Pietro
Sparse active illumination enables precise time-of-flight depth sensing as it maximizes signal-to-noise ratio for low power budgets. However, depth completion is required to produce dense depth maps for 3D perception. We address this task with realis
Externí odkaz:
http://arxiv.org/abs/2205.12918
Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly trained. In th
Externí odkaz:
http://arxiv.org/abs/2203.11049