Maxime Oquab

Learn More
Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large- scale visual recognition challenge (ILSVRC2012). The success of CNNs is attributed to their ability to learn rich mid-level image representations as opposed to hand-designed low-level features used in other image classification methods.(More)
Successful methods for visual object recognition typically rely on training datasets containing lots of richly annotated images. Detailed image annotation, e.g. by object bounding boxes, however, is both expensive and often subjective. We describe a weakly supervised convolutional neural network (CNN) for object classification that relies only on(More)
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 precise object boundaries. We address this problem by introducing two types of context-aware guidance models, additive and contrastive models, that leverage their surrounding(More)
The goal of two-sample tests is to assess whether two samples, SP ∼ P and SQ ∼ Q, are drawn from the same distribution. Perhaps intriguingly, one relatively unexplored method to build two-sample tests is the use of binary classifiers. In particular, construct a dataset by pairing the n examples in SP with a positive label, and by pairing the m examples in(More)
This note describes two simple techniques to stabilize the training of Generative Adversarial Networks (GANs) on multimodal data. First, we propose a covering initialization for the generator. This initialization pre-trains the generator to match the empirical mean and covariance of its samples with those of the real training data. Second, we propose using(More)
  • 1