Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Liao, Zukang"'
In many applications, machine learned (ML) models are required to hold some invariance qualities, such as rotation, size, intensity, and background invariance. Unlike many types of variance, the variants of background scenes cannot be ordered easily,
Externí odkaz:
http://arxiv.org/abs/2208.09286
In machine learning (ML) workflows, determining the invariance qualities of an ML model is a common testing procedure. Traditionally, invariance qualities are evaluated using simple formula-based scores, e.g., accuracy. In this paper, we show that te
Externí odkaz:
http://arxiv.org/abs/2109.12926
Autor:
Liao, Zukang
Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this problem is to
Externí odkaz:
http://arxiv.org/abs/1807.08108
This paper presents a classifier ensemble for Facial Expression Recognition (FER) based on models derived from transfer learning. The main experimentation work is conducted for facial action unit detection using feature extraction and fine-tuning con
Externí odkaz:
http://arxiv.org/abs/1807.07556
Local deep neural networks have been recently introduced for gender recognition. Although, they achieve very good performance they are very computationally expensive to train. In this work, we introduce a simplified version of local deep neural netwo
Externí odkaz:
http://arxiv.org/abs/1703.08497
Publikováno v:
2022 IEEE International Conference On Artificial Intelligence Testing (AITest).
In machine learning (ML) workflows, determining the invariance qualities of an ML model is a common testing procedure. Traditionally, invariance qualities are evaluated using simple formula-based scores, e.g., accuracy. In this paper, we show that te