Weidong Shi

Weidong Shi, Guanghui Ren, Yunpeng Chen et al.

Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the student model (i.e. to make images corresponding to the same semantics share the same embedding across different models). In this work, we focus on its application in face recognition. We observe that existing knowledge distillation models optimize the proxy tasks that force the student to mimic the teacher's behavior, instead of directly optimizing the face recognition accuracy. Consequently, the obtained student models are not guaranteed to be optimal on the target task or able to benefit from advanced constraints, such as large margin constraints (e.g. margin-based softmax). We then propose a novel method named ProxylessKD that directly optimizes face recognition accuracy by inheriting the teacher's classifier as the student's classifier to guide the student to learn discriminative embeddings in the teacher's embedding space. The proposed ProxylessKD is very easy to implement and sufficiently generic to be extended to other tasks beyond face recognition. We conduct extensive experiments on standard face recognition benchmarks, and the results demonstrate that ProxylessKD achieves superior performance over existing knowledge distillation methods.

Hadi Mansourifar, Weidong Shi

Synthetic Minority Over-sampling Technique (SMOTE) is the most popular over-sampling method. However, its random nature makes the synthesized data and even imbalanced classification results unstable. It means that in case of running SMOTE n different times, n different synthesized in-stances are obtained with n different classification results. To address this problem, we adapt the SMOTE idea in deep learning architecture. In this method, a deep neural network regression model is used to train the inputs and outputs of traditional SMOTE. Inputs of the proposed deep regression model are two randomly chosen data points which are concatenated to form a double size vector. The outputs of this model are corresponding randomly interpolated data points between two randomly chosen vectors with original dimension. The experimental results show that, Deep SMOTE can outperform traditional SMOTE in terms of precision, F1 score and Area Under Curve (AUC) in majority of test cases.

Hadi Mansourifar, Weidong Shi

Breast cancer is the most frequently reported cancer type among the women around the globe and beyond that it has the second highest female fatality rate among all cancer types. Despite all the progresses made in prevention and early intervention, early prognosis and survival prediction rates are still unsatisfactory. In this paper, we propose a novel type of perceptron called L-Perceptron which outperforms all the previous supervised learning methods by reaching 97.42 \% and 98.73 \% in terms of accuracy and sensitivity, respectively in Wisconsin Breast Cancer dataset. Experimental results on Haberman's Breast Cancer Survival dataset, show the superiority of proposed method by reaching 75.18 \% and 83.86 \% in terms of accuracy and F1 score, respectively. The results are the best reported ones obtained in 10-fold cross validation in absence of any preprocessing or feature selection.