arXiv subjects

Jiaxin Ye

Publications and source records attributed to Jiaxin Ye.

21 records · Page 2Linked to original sources

arXiv2023

Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition

Cross-corpus speech emotion recognition (SER) seeks to generalize the ability of inferring speech emotion from a well-labeled corpus to an unlabeled one, which is a rather challenging task due to the significant discrepancy between two corpora. Existing methods, typically based on unsupervised domain adaptation (UDA), struggle to learn corpus-invariant features by global distribution alignment, but unfortunately, the resulting features are mixed with corpus-specific features or not class-discriminative. To tackle these challenges, we propose a novel Emotion Decoupling aNd Alignment learning framework (EMO-DNA) for cross-corpus SER, a novel UDA method to learn emotion-relevant corpus-invariant features. The novelties of EMO-DNA are two-fold: contrastive emotion decoupling and dual-level emotion alignment. On one hand, our contrastive emotion decoupling achieves decoupling learning via a contrastive decoupling loss to strengthen the separability of emotion-relevant features from corpus-specific ones. On the other hand, our dual-level emotion alignment introduces an adaptive threshold pseudo-labeling to select confident target samples for class-level alignment, and performs corpus-level alignment to jointly guide model for learning class-discriminative corpus-invariant features across corpora. Extensive experimental results demonstrate the superior performance of EMO-DNA over the state-of-the-art methods in several cross-corpus scenarios. Source code is available at https://github.com/Jiaxin-Ye/Emo-DNA.

cs.SD↗

arXiv2023

Online Prototype Learning for Online Continual Learning

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based methods have shown promising performance. Unlike previous methods that focus on sample storage or knowledge distillation against catastrophic forgetting, this paper aims to understand why the online learning models fail to generalize well from a new perspective of shortcut learning. We identify shortcut learning as the key limiting factor for online CL, where the learned features may be biased, not generalizable to new tasks, and may have an adverse impact on knowledge distillation. To tackle this issue, we present the online prototype learning (OnPro) framework for online CL. First, we propose online prototype equilibrium to learn representative features against shortcut learning and discriminative features to avoid class confusion, ultimately achieving an equilibrium status that separates all seen classes well while learning new classes. Second, with the feedback of online prototypes, we devise a novel adaptive prototypical feedback mechanism to sense the classes that are easily misclassified and then enhance their boundaries. Extensive experimental results on widely-used benchmark datasets demonstrate the superior performance of OnPro over the state-of-the-art baseline methods. Source code is available at https://github.com/weilllllls/OnPro.

cs.CV↗

arXiv2022

Theoretical Study of the Enhancement of Light Saturation Phenomena of Krypton at Critical Ionization Photon Energies

By calculating the correlation between the total photoionization cross-section of the ground state of the Kr atom and photon energy, three particular photon energies close to the near inner orbital energy of 1.75 keV, 1.90 keV, and 14.30 keV are determined in this work. The dynamical simulation under 17.50 keV photon energy in the experimental conditions is achieved by implementing the Monte Carlo method and optimizing the photon flux modeling parameters. As a result, our calculated data are more consistent with the experimental phenomena. The light saturation phenomenon of Kr at 1.75 keV, 1.90 keV, 14.30 keV, and 17.50 keV energies is further calculated and researched using the optimized photon flux model theory. We statistically compare the main ionization paths under those four specific photon energies and calculate the population changes of various hollow atoms. The results demonstrate that the ratio of hollow atoms produced at the critical ionization photon energy is high. Furthermore, the change of position is smooth, showing the significant difference between the generation mode of ions with low photon energy and those with high photon energy, which has important reference significance for studying hollow atoms with medium and high charge states.

physics.atom-ph↗