papers

Publications (10)

cs.CV2018

Class label autoencoder for zero-shot learning

Guangfeng Lin, Caixia Fan, Wanjun Chen +2

Existing zero-shot learning (ZSL) methods usually learn a projection function between a feature space and a semantic embedding space(text or attribute space) in the training seen c…

cs.CV2017

Structure propagation for zero-shot learning

Guangfeng Lin, Yajun Chen, Fan Zhao

The key of zero-shot learning (ZSL) is how to find the information transfer model for bridging the gap between images and semantic information (texts or attributes). Existing ZSL m…

cs.CV2026

Boundary and Position Information Mining for Aerial Small Object Detection

Rongxin Huang, Guangfeng Lin, Wenbo Zhou +2

Unmanned Aerial Vehicle (UAV) applications have become increasingly prevalent in aerial photography and object recognition. However, there are major challenges to accurately captur…

cs.CV2020

High-order structure preserving graph neural network for few-shot learning

Guangfeng Lin, Ying Yang, Yindi Fan +3

Few-shot learning can find the latent structure information between the prior knowledge and the queried data by the similarity metric of meta-learning to construct the discriminati…

cs.LG2019

Structure fusion based on graph convolutional networks for semi-supervised classification

Guangfeng Lin, Jing Wang, Kaiyang Liao +2

Suffering from the multi-view data diversity and complexity for semi-supervised classification, most of existing graph convolutional networks focus on the networks architecture con…

cs.CV2025

Frequency-Domain Fusion Transformer for Image Inpainting

Sijin He, Guangfeng Lin, Tao Li +1

Image inpainting plays a vital role in restoring missing image regions and supporting high-level vision tasks, but traditional methods struggle with complex textures and large occl…

cs.CV2019

Transfer feature generating networks with semantic classes structure for zero-shot learning

Guangfeng Lin, Wanjun Chen, Kaiyang Liao +2

Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data…

cs.CV2020

Deep graph learning for semi-supervised classification

Guangfeng Lin, Xiaobing Kang, Kaiyang Liao +2

Graph learning (GL) can dynamically capture the distribution structure (graph structure) of data based on graph convolutional networks (GCN), and the learning quality of the graph…

cs.CV2025

Scalable Class-Incremental Learning Based on Parametric Neural Collapse

Chuangxin Zhang, Guangfeng Lin, Enhui Zhao +2

Incremental learning often encounter challenges such as overfitting to new data and catastrophic forgetting of old data. Existing methods can effectively extend the model for new t…

cs.CV2024

Gabor-guided transformer for single image deraining

Sijin He, Guangfeng Lin

Image deraining have have gained a great deal of attention in order to address the challenges posed by the effects of harsh weather conditions on visual tasks. While convolutional…