259 citations · 978 across the 60 of their papers we have counts for
11 papers · 1 filter
Transductive Zero-Shot Learning using Cross-Modal CycleGAN
Patrick Bordes, Eloi Zablocki, Benjamin Piwowarski +1
In Computer Vision, Zero-Shot Learning (ZSL) aims at classifying unseen classes -- classes for which no matching training image exists. Most of ZSL works learn a cross-modal mappin…
Stochastic sparse adversarial attacks
Manon Césaire, Lucas Schott, Hatem Hajri +2
This paper introduces stochastic sparse adversarial attacks (SSAA), standing as simple, fast and purely noise-based targeted and untargeted attacks of neural network classifiers (N…
PARENTing via Model-Agnostic Reinforcement Learning to Correct Pathological Behaviors in Data-to-Text Generation
Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten +1
In language generation models conditioned by structured data, the classical training via maximum likelihood almost always leads models to pick up on dataset divergence (i.e., hallu…
Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
Yuan Yin, Vincent Le Guen, Jérémie Dona +4
Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields. While purel…
Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!
Bruno Taillé, Vincent Guigue, Geoffrey Scoutheeten +1
Despite efforts to distinguish three different evaluation setups (Bekoulis et al., 2018), numerous end-to-end Relation Extraction (RE) articles present unreliable performance compa…
A Principle of Least Action for the Training of Neural Networks
Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac +1
Neural networks have been achieving high generalization performance on many tasks despite being highly over-parameterized. Since classical statistical learning theory struggles to…
PDE-Driven Spatiotemporal Disentanglement
Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier +1
A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differen…
Incorporating Visual Semantics into Sentence Representations within a Grounded Space
Patrick Bordes, Eloi Zablocki, Laure Soulier +2
Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same represent…
What BERT Sees: Cross-Modal Transfer for Visual Question Generation
Thomas Scialom, Patrick Bordes, Paul-Alexis Dray +2
Pre-trained language models have recently contributed to significant advances in NLP tasks. Recently, multi-modal versions of BERT have been developed, using heavy pre-training rel…
Stochastic Latent Residual Video Prediction
Jean-Yves Franceschi, Edouard Delasalles, Mickaël Chen +2
Designing video prediction models that account for the inherent uncertainty of the future is challenging. Most works in the literature are based on stochastic image-autoregressive…
Contextualized Embeddings in Named-Entity Recognition: An Empirical Study on Generalization
Bruno Taillé, Vincent Guigue, Patrick Gallinari
Contextualized embeddings use unsupervised language model pretraining to compute word representations depending on their context. This is intuitively useful for generalization, esp…