57 citations · 69 across the 16 of their papers we have counts for
8 papers · 1 filter
Generating meta-learning tasks to evolve parametric loss for classification learning
Zhaoyang Hai, Xiabi Liu, Yuchen Ren +1
The field of meta-learning has seen a dramatic rise in interest in recent years. In existing meta-learning approaches, learning tasks for training meta-models are usually collected…
Mining the Weights Knowledge for Optimizing Neural Network Structures
Mengqiao Han, Xiabi Liu, Zhaoyang Hai +1
Knowledge embedded in the weights of the artificial neural network can be used to improve the network structure, such as in network compression. However, the knowledge is set up by…
A Novel Structured Natural Gradient Descent for Deep Learning
Weihua Liu, Xiabi Liu
Natural gradient descent (NGD) provided deep insights and powerful tools to deep neural networks. However the computation of Fisher information matrix becomes more and more difficu…
A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation
Xi Liu, Xiabi Liu, Huiyu Li +1
Image co-segmentation has attracted a lot of attentions in computer vision community. In this paper, we propose a new approach to image co-segmentation through introducing the dens…
Explore the Knowledge contained in Network Weights to Obtain Sparse Neural Networks
Mengqiao Han, Xiabi Liu, Zhaoyang Hai +1
Sparse neural networks are important for achieving better generalization and enhancing computation efficiency. This paper proposes a novel learning approach to obtain sparse fully…
Improving Image co-segmentation via Deep Metric Learning
Zhengwen Li, Xiabi Liu
Deep Metric Learning (DML) is helpful in computer vision tasks. In this paper, we firstly introduce DML into image co-segmentation. We propose a novel Triplet loss for Image Segmen…
Fusing Medical Image Features and Clinical Features with Deep Learning for Computer-Aided Diagnosis
Songxiao Yang, Xiabi Liu, Zhongshu Zheng +2
Current Computer-Aided Diagnosis (CAD) methods mainly depend on medical images. The clinical information, which usually needs to be considered in practical clinical diagnosis, has…
Evolving parametrized Loss for Image Classification Learning on Small Datasets
Zhaoyang Hai, Xiabi Liu
This paper proposes a meta-learning approach to evolving a parametrized loss function, which is called Meta-Loss Network (MLN), for training the image classification learning on sm…