34 citations · 77 across the 12 of their papers we have counts for
14 papers
Opti-CAM: Optimizing saliency maps for interpretability
Hanwei Zhang, Felipe Torres, Ronan Sicre +2
Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as sa…
Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?
Mitja Nikolaus, Emmanuelle Salin, Stephane Ayache +2
Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the e…
Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
Kais Hariz, Hachem Kadri, Stéphane Ayache +2
We study the implicit regularization effects of deep learning in tensor factorization. While implicit regularization in deep matrix and 'shallow' tensor factorization via linear an…
ChaLearn Looking at People: Inpainting and Denoising challenges
Sergio Escalera, Marti Soler, Stephane Ayache +6
Dealing with incomplete information is a well studied problem in the context of machine learning and computational intelligence. However, in the context of computer vision, the pro…
Implicit Regularization in Deep Tensor Factorization
Paolo Milanesi, Hachem Kadri, Stéphane Ayache +1
Attempts of studying implicit regularization associated to gradient descent (GD) have identified matrix completion as a suitable test-bed. Late findings suggest that this phenomeno…
Distillation of Weighted Automata from Recurrent Neural Networks using a Spectral Approach
Remi Eyraud, Stephane Ayache
This paper is an attempt to bridge the gap between deep learning and grammatical inference. Indeed, it provides an algorithm to extract a (stochastic) formal language from any recu…