Zenglin Shi

TL;DR: This work proposes a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL), which deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities.

TL;DR: This work presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017.

TL;DR: Zhang et al. as discussed by the authors proposed counting with focus from segmentation and global density, where the ratio of point annotations to image pixels is used in another branch to regularize the overall density estimation.

TL;DR: The core of the approach is the generalization of negative correlation learning that has been shown, both theoretically and empirically, to work well for non-deep regression problems, and shows that each sub-problem in the proposed method has less Rademacher Complexity and thus is easier to optimize.

TL;DR: Experimental results on several image benchmarks show that rank-based pooling outperforms the existing pooling methods in classification performance, and this work presents a novel criterion to analyze the discriminant ability of variouspooling methods, which is heavily under-researched in machine learning and computer vision community.