L
Liang Gao
Researcher at National University of Defense Technology
Publications - 5
Citations - 43
Liang Gao is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 2, co-authored 2 publications receiving 18 citations.
Papers
More filters
Journal ArticleDOI
An Adversarial Feature Distillation Method for Audio Classification
TL;DR: A distillation method is proposed which transfers knowledge from well-trained networks to a small network, and the method can compress model size while improving audio classification precision and demonstrate that the small network can provide better performance.
Journal ArticleDOI
Multistructure-Based Collaborative Online Distillation
TL;DR: A cross-architecture online-distillation approach that uses the ensemble method to aggregate networks of different structures, thus forming better teachers than traditional distillation methods and achieves strong network-performance improvement.
Proceedings ArticleDOI
CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition
Wenqi Zhao,Liang Gao +1 more
TL;DR: This paper proposes CoMER, a model that adopts the coverage information in the transformer decoder, and proposes a novel Attention Refinement Module (ARM) to refine the attention weights with past alignment information without hurting its parallelism.
Journal ArticleDOI
A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detection
TL;DR: Results show that DKAN outperforms other methods on various few-shot scenes, up to 6.65% on the mean Average Precision metric, which proves the effectiveness of the proposed method.
Proceedings ArticleDOI
Adversarial unsupervised domain adaptive inland vessel detection method
Liang Gao,Gao Shu +1 more
TL;DR: In this paper , an adversarial unsupervised domain adaptive method is proposed, using labeled sunny samples and unlabeled foggy samples, which can adaptively detect ship targets in foggy conditions.