no code implementations • 15 Jan 2024 • Zukang Liao, Min Chen
In this work, we present a novel approach for building an image similarity model based on labelled data in the form of A:R vs B:R. We address the challenges of sparse sampling in the image space (R, A, B) and biases in the models trained with context-based data by using an ensemble model.
no code implementations • 19 Aug 2022 • Zukang Liao, Pengfei Zhang, Min Chen
This ontology enables (i) efficient and meaningful search for background scenes of different semantic distances to a target image, (ii) quantitative control of the distribution and sparsity of the sampled background scenes, and (iii) quality assurance using visual representations of invariance testing results (referred to as variance matrices).
1 code implementation • 27 Sep 2021 • Zukang Liao, Pengfei Zhang, Min Chen
In this paper, we show that testing the invariance qualities of ML models may result in complex visual patterns that cannot be classified using simple formulas.
no code implementations • 21 Jul 2018 • Zukang Liao
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.
no code implementations • 19 Jul 2018 • Yen Khye Lim, Zukang Liao, Stavros Petridis, Maja Pantic
This paper presents a classifier ensemble for Facial Expression Recognition (FER) based on models derived from transfer learning.
no code implementations • 24 Mar 2017 • Zukang Liao, Stavros Petridis, Maja Pantic
We tested the proposed modified local deep neural networks approach on the LFW and Adience databases for the task of gender and age classification.