1.4k citations · 2.6k across the 79 of their papers we have counts for
16 papers · 1 filter
QUEST: Quantized embedding space for transferring knowledge
Himalaya Jain, Spyros Gidaris, Nikos Komodakis +2
Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing…
This dataset does not exist: training models from generated images
Victor Besnier, Himalaya Jain, Andrei Bursuc +2
Current generative networks are increasingly proficient in generating high-resolution realistic images. These generative networks, especially the conditional ones, can potentially…
Addressing Failure Prediction by Learning Model Confidence
Charles Corbière, Nicolas Thome, Avner Bar-Hen +2
Assessing reliably the confidence of a deep neural network and predicting its failures is of primary importance for the practical deployment of these models. In this paper, we prop…
REVE: Regularizing Deep Learning with Variational Entropy Bound
Antoine Saporta, Yifu Chen, Michael Blot +1
Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization…
Riemannian batch normalization for SPD neural networks
Daniel Brooks, Olivier Schwander, Frederic Barbaresco +2
Covariance matrices have attracted attention for machine learning applications due to their capacity to capture interesting structure in the data. The main challenge is that one ne…
Boosting Few-Shot Visual Learning with Self-Supervision
Spyros Gidaris, Andrei Bursuc, Nikos Komodakis +2
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimiz…
DualDis: Dual-Branch Disentangling with Adversarial Learning
Thomas Robert, Nicolas Thome, Matthieu Cord
In computer vision, disentangling techniques aim at improving latent representations of images by modeling factors of variation. In this paper, we propose DualDis, a new auto-encod…
RUBi: Reducing Unimodal Biases in Visual Question Answering
Remi Cadene, Corentin Dancette, Hedi Ben-younes +2
Visual Question Answering (VQA) is the task of answering questions about an image. Some VQA models often exploit unimodal biases to provide the correct answer without using the ima…
Zero-Shot Semantic Segmentation
Maxime Bucher, Tuan-Hung Vu, Matthieu Cord +1
Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation:…
SEMEDA: Enhancing Segmentation Precision with Semantic Edge Aware Loss
Yifu Chen, Arnaud Dapogny, Matthieu Cord
While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy.…
The Missing Data Encoder: Cross-Channel Image Completion\\with Hide-And-Seek Adversarial Network
Arnaud Dapogny, Matthieu Cord, Patrick Perez
Image completion is the problem of generating whole images from fragments only. It encompasses inpainting (generating a patch given its surrounding), reverse inpainting/extrapolati…
SoDeep: a Sorting Deep net to learn ranking loss surrogates
Martin Engilberge, Louis Chevallier, Patrick Pérez +1
Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability preven…
DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild
Arnaud Dapogny, Kévin Bailly, Matthieu Cord
Face Alignment is an active computer vision domain, that consists in localizing a number of facial landmarks that vary across datasets. State-of-the-art face alignment methods eith…
DADA: Depth-aware Domain Adaptation in Semantic Segmentation
Tuan-Hung Vu, Himalaya Jain, Maxime Bucher +2
Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it h…
MUREL: Multimodal Relational Reasoning for Visual Question Answering
Remi Cadene, Hedi Ben-younes, Matthieu Cord +1
Multimodal attentional networks are currently state-of-the-art models for Visual Question Answering (VQA) tasks involving real images. Although attention allows to focus on the vis…
BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection
Hedi Ben-younes, Rémi Cadene, Nicolas Thome +1
Multimodal representation learning is gaining more and more interest within the deep learning community. While bilinear models provide an interesting framework to find subtle combi…