137 citations · 219 across the 3 of their papers we have counts for
3 papers
cs.LG2020★ 25 cited
Direction Concentration Learning: Enhancing Congruency in Machine Learning
Yan Luo, Yongkang Wong, Mohan S. Kankanhalli +1
One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and th…
cs.CV2019★ 57 cited
-softmax: Improving Intra-class Compactness and Inter-class Separability of Features
Yan Luo, Yongkang Wong, Mohan Kankanhalli +1
Intra-class compactness and inter-class separability are crucial indicators to measure the effectiveness of a model to produce discriminative features, where intra-class compactnes…
cs.LG2015★ 137 cited
Foveation-based Mechanisms Alleviate Adversarial Examples
Yan Luo, Xavier Boix, Gemma Roig +2
We show that adversarial examples, i.e., the visually imperceptible perturbations that result in Convolutional Neural Networks (CNNs) fail, can be alleviated with a mechanism based…