Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition. ICASSP 25
Down-Sampling Inter-Layer Adapter for Parameter and Computation Efficient Ultra-Fine-Grained Image Recognition. ECCV EFM Workshop 24
Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers. ISCAS 25
Anime Character Recognition using Intermediate Features Aggregation. ISCAS 2022
IFACD: Intermediate Features Augmented Contrastive Distillation. ICLR CSS Workshop 2022
Research Experience
Conducted doctoral research at NYCU focusing on the design of efficient deep learning models.
Education
Received B.S. degree in Energy Engineering from National Cheng Kung University (NCKU), Tainan, Taiwan, in 2019. Enrolled in National Yang Ming Chiao Tung University (NYCU) to pursue M.S. and Ph.D. degrees in Electrical Engineering and Computer Science (EECS) in 2019 and 2021, respectively. Co-supervised by Professor Bo-Cheng Lai and Professor Min-Chun Hu.
Background
From Panama, research interests include the design of efficient deep learning models, particularly in time-series heart-rate monitoring, model compression using knowledge distillation and self-supervised learning, and efficient fine-grained image recognition systems.