User profiles for Maxime Oquab
Maxime OquabFacebook AI Research Verified email at fb.com Cited by 6920 |
Learning and transferring mid-level image representations using convolutional neural networks
Convolutional neural networks (CNN) have recently shown outstanding image classification
performance in the large-scale visual recognition challenge (ILSVRC2012). The success of …
performance in the large-scale visual recognition challenge (ILSVRC2012). The success of …
Is object localization for free?-weakly-supervised learning with convolutional neural networks
Successful visual object recognition methods typically rely on training datasets containing
lots of richly annotated images. Annotating object bounding boxes is both expensive and …
lots of richly annotated images. Annotating object bounding boxes is both expensive and …
Low bandwidth video-chat compression using deep generative models
To unlock video chat for hundreds of millions of people hindered by poor connectivity or
unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device …
unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device …
Dinov2: Learning robust visual features without supervision
The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision. These …
quantities of data have opened the way for similar foundation models in computer vision. These …
Revisiting classifier two-sample tests
D Lopez-Paz, M Oquab - arXiv preprint arXiv:1610.06545, 2016 - arxiv.org
The goal of two-sample tests is to assess whether two samples, $S_P \sim P^n$ and $S_Q \sim
Q^m$, are drawn from the same distribution. Perhaps intriguingly, one relatively …
Q^m$, are drawn from the same distribution. Perhaps intriguingly, one relatively …
Contextlocnet: Context-aware deep network models for weakly supervised localization
We aim to localize objects in images using image-level supervision only. Previous approaches
to this problem mainly focus on discriminative object regions and often fail to locate …
to this problem mainly focus on discriminative object regions and often fail to locate …
Vision transformers need registers
Transformers have recently emerged as a powerful tool for learning visual representations. In
this paper, we identify and characterize artifacts in feature maps of both supervised and self…
this paper, we identify and characterize artifacts in feature maps of both supervised and self…
[PDF][PDF] Weakly supervised object recognition with convolutional neural networks
Successful visual object recognition methods typically rely on training datasets containing
lots of richly annotated images. Annotating object bounding boxes is both expensive and …
lots of richly annotated images. Annotating object bounding boxes is both expensive and …
Co-training 2L submodels for visual recognition
This paper introduces submodel co-training, a regularization method related to co-training,
self-distillation and stochastic depth. Given a neural network to be trained, for each sample …
self-distillation and stochastic depth. Given a neural network to be trained, for each sample …
Dimensionality and ramping: Signatures of sentence integration in the dynamics of brains and deep language models
A sentence is more than the sum of its words: its meaning depends on how they combine with
one another. The brain mechanisms underlying such semantic composition remain poorly …
one another. The brain mechanisms underlying such semantic composition remain poorly …