259 citations · 978 across the 60 of their papers we have counts for
7 papers · 1 filter
Diverse Weight Averaging for Out-of-Distribution Generalization
Alexandre Ramé, Matthieu Kirchmeyer, Thibaud Rahier +3
Standard neural networks struggle to generalize under distribution shifts in computer vision. Fortunately, combining multiple networks can consistently improve out-of-distribution…
Explainable Deep Image Classifiers for Skin Lesion Diagnosis
Carlo Metta, Andrea Beretta, Riccardo Guidotti +4
A key issue in critical contexts such as medical diagnosis is the interpretability of the deep learning models adopted in decision-making systems. Research in eXplainable Artificia…
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 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…
Unsupervised Adversarial Image Inpainting
Arthur Pajot, Emmanuel de Bezenac, Patrick Gallinari
We consider inpainting in an unsupervised setting where there is neither access to paired nor unpaired training data. The only available information is provided by the uncomplete o…
Context-Aware Zero-Shot Learning for Object Recognition
Eloi Zablocki, Patrick Bordes, Benjamin Piwowarski +2
Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only…
Sequentially Generated Instance-Dependent Image Representations for Classification
Gabriel Dulac-Arnold, Ludovic Denoyer, Nicolas Thome +2
In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns…