ﻻ يوجد ملخص باللغة العربية
This work presents a new deep learning approach for keystroke biometrics based on a novel Distance Metric Learning method (DML). DML maps input data into a learned representation space that reveals a semantic structure based on distances. In this work, we propose a novel DML method specifically designed to address the challenges associated to free-text keystroke identification where the classes used in learning and inference are disjoint. The proposed SetMargin Loss (SM-L) extends traditional DML approaches with a learning process guided by pairs of sets instead of pairs of samples, as done traditionally. The proposed learning strategy allows to enlarge inter-class distances while maintaining the intra-class structure of keystroke dynamics. We analyze the resulting representation space using the mathematical problem known as Circle Packing, which provides neighbourhood structures with a theoretical maximum inter-class distance. We finally prove experimentally the effectiveness of the proposed approach on a challenging task: keystroke biometric identification over a large set of 78,000 subjects. Our method achieves state-of-the-art accuracy on a comparison performed with the best existing approaches.
We consider the online problem of packing circles into a square container. A sequence of circles has to be packed one at a time, without knowledge of the following incoming circles and without moving previously packed circles. We present an algorithm
Extreme Learning Machine is a powerful classification method very competitive existing classification methods. It is extremely fast at training. Nevertheless, it cannot perform face verification tasks properly because face verification tasks require
This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$. We find a majority of loss functions, including the triplet l
The most popular face recognition benchmarks assume a distribution of subjects without much attention to their demographic attributes. In this work, we perform a comprehensive discrimination-aware experimentation of deep learning-based face recogniti
Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation, and even vi