1.4k citations · 2.6k across the 79 of their papers we have counts for
21 papers · 1 filter
Augmenting Convolutional networks with attention-based aggregation
Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby +4
We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning. We replace the final average pooling by an attention-based aggre…
CSG0: Continual Urban Scene Generation with Zero Forgetting
Himalaya Jain, Tuan-Hung Vu, Patrick Pérez +1
With the rapid advances in generative adversarial networks (GANs), the visual quality of synthesised scenes keeps improving, including for complex urban scenes with applications to…
Embedding Arithmetic of Multimodal Queries for Image Retrieval
Guillaume Couairon, Matthieu Cord, Matthijs Douze +1
Latent text representations exhibit geometric regularities, such as the famous analogy: queen is to king what woman is to man. Such structured semantic relations were not demonstra…
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis
Thomas Fel, Remi Cadene, Mathieu Chalvidal +3
We describe a novel attribution method which is grounded in Sensitivity Analysis and uses Sobol indices. Beyond modeling the individual contributions of image regions, Sobol indice…
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion
Arthur Douillard, Alexandre Ramé, Guillaume Couairon +1
Deep network architectures struggle to continually learn new tasks without forgetting the previous tasks. A recent trend indicates that dynamic architectures based on an expansion…
STEEX: Steering Counterfactual Explanations with Semantics
Paul Jacob, Éloi Zablocki, Hédi Ben-Younes +3
As deep learning models are increasingly used in safety-critical applications, explainability and trustworthiness become major concerns. For simple images, such as low-resolution f…
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord +1
Pruning Deep Neural Networks (DNNs) is a prominent field of study in the goal of inference runtime acceleration. In this paper, we introduce a novel data-free pruning protocol RED+…
Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
Antoine Saporta, Tuan-Hung Vu, Matthieu Cord +1
In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model…
Raising context awareness in motion forecasting
Hédi Ben-Younes, Éloi Zablocki, Mickaël Chen +2
Learning-based trajectory prediction models have encountered great success, with the promise of leveraging contextual information in addition to motion history. Yet, we find that s…
LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
Florent Bartoccioni, Éloi Zablocki, Patrick Pérez +2
Vision-based depth estimation is a key feature in autonomous systems, which often relies on a single camera or several independent ones. In such a monocular setup, dense depth is o…
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
Alexandre Rame, Corentin Dancette, Matthieu Cord
Learning robust models that generalize well under changes in the data distribution is critical for real-world applications. To this end, there has been a growing surge of interest…
Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
Arthur Douillard, Yifu Chen, Arnaud Dapogny +1
Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power.…
ResMLP: Feedforward networks for image classification with data-efficient training
Hugo Touvron, Piotr Bojanowski, Mathilde Caron +8
We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which…
Semantic Palette: Guiding Scene Generation with Class Proportions
Guillaume Le Moing, Tuan-Hung Vu, Himalaya Jain +2
Despite the recent progress of generative adversarial networks (GANs) at synthesizing photo-realistic images, producing complex urban scenes remains a challenging problem. Previous…
RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord +1
Deep Neural Networks (DNNs) are ubiquitous in today's computer vision land-scape, despite involving considerable computational costs. The mainstream approaches for runtime accelera…
Going deeper with Image Transformers
Hugo Touvron, Matthieu Cord, Alexandre Sablayrolles +2
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the opti…
Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering
Corentin Dancette, Remi Cadene, Damien Teney +1
We introduce an evaluation methodology for visual question answering (VQA) to better diagnose cases of shortcut learning. These cases happen when a model exploits spurious statisti…
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
Alexandre Rame, Remy Sun, Matthieu Cord
Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork lea…
Training data-efficient image transformers & distillation through attention
Hugo Touvron, Matthieu Cord, Matthijs Douze +3
Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained…
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
Alexandre Rame, Matthieu Cord
Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also…
Explainability of deep vision-based autonomous driving systems: Review and challenges
Éloi Zablocki, Hédi Ben-Younes, Patrick Pérez +1
This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several facets and the need for ex…