hierarchical network with decoupled knowledge distillation for speech emotion recognition

Zhao, Zhigang; Wang, Huan; Wang, Haishuai; Schuller, Björn W.

doi:10.48550/arxiv.2303.05134

Cited by 1 publication

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tang et al [32] distill knowledge from the BERT model [33] into a single-layer bidirectional long short-term memory for natural language processing sentiment classification. DKDFMH [34] uses a fused multihead attention mechanism to employ decoupled knowledge distillation in CNNs, helping the method focus on the distinctions between sentiment features.…”

Section: Knowledge Distillation For Sentimentsmentioning

confidence: 99%

Zero-Shot Visual Sentiment Prediction via Cross-Domain Knowledge Distillation

Moroto,

Ye,

Maeda

et al. 2024

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

There are various sentiment theories for categorizing human sentiments into several discrete sentiment categories, which means that the theory used for training sentiment prediction methods does not always match that used in the test phase. As a solution to this problem, zero-shot visual sentiment prediction methods have been proposed to predict unseen sentiments for which no images are available in the training phase. However, the training of these previous zero-shot methods relies on a single sentiment theory, which limits their ability to handle sentiments from other theories. Thus, this paper proposes a more robust zeroshot visual sentiment prediction method that can handle cross-domain sentiments defined in different sentiment theories. Specifically, by focusing on the fact that sentiments are abstract concepts common to humans regardless of whether their theories are different, we incorporate knowledge distillation into our method to construct a teacher-student model that can train the implicit relationships between sentiments defined in different sentiment theories. Furthermore, to enhance sentiment discrimination capability and strengthen the implicit relationships between sentiments, we introduce a novel sentiment loss between the teacher and student models. In this way, our model becomes robust to unseen sentiments by exploiting the implicit relationships between sentiments. The contributions of this paper are the introduction of knowledge distillation and a novel sentiment loss between the teacher and student models for zero-shot visual sentiment prediction, and improved performance of zero-shot visual sentiment prediction. Experiments on several open datasets demonstrate the effectiveness of the proposed method.INDEX TERMS Visual sentiment prediction, zero-shot learning, knowledge distillation, cross-domain analysis, text analysis.

show abstract

Section: Knowledge Distillation For Sentimentsmentioning

confidence: 99%