activity
20162025
most citedTraining data-efficient image transformers & distillation through attention

150 citations · 656 across the 62 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

17 papers · 2 filters

cs.CV2021★ 30 cited

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…

cs.CV2021

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…

cs.CV2021

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…

cs.CV2021★ 11 cited

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…

cs.CV2021★ 1 cited

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…

cs.CV2021

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…