activity
20152023
most citedAn Overview of Deep Semi-Supervised Learning

244 citations · 355 across the 15 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2022

Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling

Etienne Bennequin, Myriam Tami, Antoine Toubhans +1

Every day, a new method is published to tackle Few-Shot Image Classification, showing better and better performances on academic benchmarks. Nevertheless, we observe that these cur…

cs.CV2022

Optimizing Active Learning for Low Annotation Budgets

Umang Aggarwal, Adrian Popescu, Céline Hudelot

When we can not assume a large amount of annotated data , active learning is a good strategy. It consists in learning a model on a small amount of annotated data (annotation budget…

cs.CV2020

AVAE: Adversarial Variational Auto Encoder

Antoine Plumerault, Hervé Le Borgne, Céline Hudelot

Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN). GANs can produce realistic image…

cs.CV20202 cited

Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification

Martin Charachon, Céline Hudelot, Paul-Henry Cournède +2

Explaining decisions of black-box classifiers is paramount in sensitive domains such as medical imaging since clinicians confidence is necessary for adoption. Various explanation a…

cs.CV2020

Spatial Contrastive Learning for Few-Shot Classification

Yassine Ouali, Céline Hudelot, Myriam Tami

In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent r…

cs.CV2020

Autoregressive Unsupervised Image Segmentation

Yassine Ouali, Céline Hudelot, Myriam Tami

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspirati…