Generalization by Visual Attention

Most deep learning models fail to generalize in production. Indeed, sometimes data used during training does not completely reflect the deployed environment. The test data is then considered out-of-distribution compared to the training data. In this paper, we focus on out-of-distribution performance for image classification. In fact,...

One Pose Fits All: A novel kinematic approach to 3D human pose estimation

3D human pose estimation is a widely researched computer vision task that could be applied in scenarios such as virtual reality and human-robot interaction. With the lack of depth information, 3D estimation from monocular images is an inherently ambiguous problem. On top of that, unrealistic human poses have been overlooked in the majority of...

Using object-specific frequency information from labeled data to improve a CNN’s robustness to adversarial attacks

Convolutional Neural Networks are particularly vulnerable to attacks that manipulate their data, which are usually called adversarial attacks. In this paper, a method of filtering images using the Fast Fourier Transform is explored, along with its potential to be used as a defense mechanism to such attacks. The main contribution that differs...