Chinese Academy of Sciences, China
Director of NLPR; IEEE and IAPR Fellow
Speech Title: Deep Prototype Learning for Robust Pattern Recognition
Abstract: Existing pattern classification studies mostly concern the generalized classification accuracy, but ignore the rejection and robustness in open world. In recent years, deep learning methods achieved huge successes in pattern recognition, but the popular deep neural networks show inferior generalization when training with small sample and poor robustness to noise and outlier. In the talk, I first explain the robustness of pattern recognition, and introduce some methods for improving the robustness from the viewpoint of rejection. The rejection methods fall in two categories: ambiguity rejection and outlier rejection, which are based on different models and learning methods. I will give the formulations of two rejection modes and introduce some methods. Last, I will introduce a newly proposed deep learning method for robust pattern classification: deep convolutional prototype learning (CPL). The CPL uses a prototype classifier for classification, which is inherently robust to outlier. And combining with feature learning by convolutional neural network (CNN), the CPL yields high classification accuracy. Through regularization based on maximum likelihood (ML), the generalization performance on small sample and robustness can be further improved. The CPL model also shows potential in domain adaptation, online learning, novel class discovery, and so on.
Shenzhen University, China
Director of Computer Vision Institute and China-UK Joint Research Lab for Visual Information Processing
Speech Title: Deep Learning for Medical Image Analysis
Abstract: In this talk, I will mainly introduce deep learning and its applications in medical image analysis. Our work using facial analysis for depression analysis will be introduced and followed by our recent work in applying deep neural network for pathology based autoimmune disease, gastric and breast cancer diagnosis. Patch based strategy will be elaborated to address the small sample problem. Finally, Lung nodule detection and ophthalmology will be introduced.
Inspur USA Inc, USA
Speech Title: Edge-Preserving Image Denoising Based on Orthogonal Wavelet Transform and Level Sets
The level set approach has the potential to accomplish simultaneous noise reduction and edge preservation when it is used for image denoising. However, this kind of techniques is not very efficient for denoising very noisy images for their non-reliable edge-stopping criterion in the partial differential equation (PDE). In addition, the numerical calculation of curvature and other partial derivatives in the PDE is very sensitive to noise. In this paper, a new algorithm is developed to tackle such problems. Our idea is to first decompose the noisy image with the orthogonal wavelet transform (OWT) and then we only filter the noisy wavelet coefficients at the three finest scales without touching the wavelet coefficients at higher levels for reducing noise while preserving edge-related coefficients. The level-set based curve evolution is finally performed on the less-noisy image reconstructed from the denoised wavelet coefficients. Thus, the PDE model can be optimized by removing the Gaussian smoothing component. Furthermore, the numerical calculation of all partial derivatives in the PDE is influenced by less noise and the selective denoising becomes more efficient. Experimental results show that the proposed algorithm outperforms the conventional level set methods and generates state-of-the-art denoising results in edge preservation and noise reduction.