1.4k citations · 2.6k across the 79 of their papers we have counts for
13 papers · 1 filter
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
Spyros Gidaris, Andrei Bursuc, Gilles Puy +3
Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a…
Confidence Estimation via Auxiliary Models
Charles Corbière, Nicolas Thome, Antoine Saporta +3
Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper…
Detecting 32 Pedestrian Attributes for Autonomous Vehicles
Taylor Mordan, Matthieu Cord, Patrick Pérez +1
Pedestrians are arguably one of the most safety-critical road users to consider for autonomous vehicles in urban areas. In this paper, we address the problem of jointly detecting p…
Grafit: Learning fine-grained image representations with coarse labels
Hugo Touvron, Alexandre Sablayrolles, Matthijs Douze +2
This paper tackles the problem of learning a finer representation than the one provided by training labels. This enables fine-grained category retrieval of images in a collection a…
PLOP: Learning without Forgetting for 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.…
Powers of layers for image-to-image translation
Hugo Touvron, Matthijs Douze, Matthieu Cord +1
We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc. We start from an image autoe…
Overcoming Statistical Shortcuts for Open-ended Visual Counting
Corentin Dancette, Remi Cadene, Xinlei Chen +1
Machine learning models tend to over-rely on statistical shortcuts. These spurious correlations between parts of the input and the output labels does not hold in real-world setting…
Insights from the Future for Continual Learning
Arthur Douillard, Eduardo Valle, Charles Ollion +2
Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting. In this…
ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
Antoine Saporta, Tuan-Hung Vu, Matthieu Cord +1
While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or we…
Deep Entwined Learning Head Pose and Face Alignment Inside an Attentional Cascade with Doubly-Conditional fusion
Arnaud Dapogny, Kévin Bailly, Matthieu Cord
Head pose estimation and face alignment constitute a backbone preprocessing for many applications relying on face analysis. While both are closely related tasks, they are generally…
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning
Arthur Douillard, Matthieu Cord, Charles Ollion +2
Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learn…
Handling new target classes in semantic segmentation with domain adaptation
Maxime Bucher, Tuan-Hung Vu, Matthieu Cord +1
In this work, we define and address a novel domain adaptation (DA) problem in semantic scene segmentation, where the target domain not only exhibits a data distribution shift w.r.t…
Learning Representations by Predicting Bags of Visual Words
Spyros Gidaris, Andrei Bursuc, Nikos Komodakis +2
Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work…