Jingyu Li

Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification

2022 · arXiv (Cornell University)

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving the model performance. This paper presents …

Smooth Distribution and Depth-Focused Distillation-Based Class-Incremental Learning for SAR Target Detection

2025 · IEEE Transactions on Geoscience and Remote Sensing

Incremental learning methods can overcome the problem of catastrophic forgetting in synthetic aperture radar (SAR) target detection models when continuously learning new class data. However, due to the characteristics of SAR images, such as large …