Alzheimer’s disease (AD) is one of the most common neurodegenerative diseases. Accurate diagnosis of mild cognitive impairment (MCI) in the prodromal stage of AD can delay onset. Therefore, the early diagnosis of AD is particularly essential. The convolutional neural network (CNN) extracts feature of image layer-by-layer, and the observed features are obtained by setting different receptive fields. However, the brain structure is very complicated, and the etiology of AD is unknown, in addition, most of the existing methods do not consider the details and overall structure of the image. To address this issue, we propose a novel multi-scale convolutional neural network (MSCNet) to enhance the model’s feature representation ability. A channel attention mechanism is introduced to improve the interdependence between channels and adaptively recalibrate the channel direction’s characteristic response. To verify the effectiveness of our method, we segment the original MRI data to obtain white matter (WM) and gray matter (GM) datasets and train the model. Extensive experiments show that our method obtains the state-of-the-art performance with fewer parameters and lower computational complexity. 

Diagnosis of Alzheimer’s disease via an attention-based multi-scale convolutional neural network

An effective risk identification method for power fence operation based on neighborhood correlation network and vector calculation

Deep learning based object detection for resource constrained devices: Systematic review, future trends and challenges ahead

Local weight coupled network: multi-modal unequal semi-supervised domain adaptation

DRNet: Dual-stage refinement network with boundary inference for RGB-D semantic segmentation of indoor scenes

Current state-of-the-art two-stage detectors heavily rely on region proposals to guide the accurate detection for objects. In previous region proposal approaches, the interaction between different functional modules is correlated weakly, which limits or decreases the performance of region proposal approaches. In this paper, we propose a novel two-stage strong correlation learning framework, abbreviated as SC-RPN, which aims to set up stronger relationship among different modules in the region proposal task. Firstly, we propose a Light-weight IoU-Mask branch to predict intersection-over-union (IoU) mask and refine region classification scores as well, it is used to prevent high-quality region proposals from being filtered. Furthermore, a sampling strategy named Size-Aware Dynamic Sampling (SADS) is proposed to ensure sampling consistency between different stages. In addition, point-based representation is exploited to generate region proposals with stronger fitting ability. Without bells and whistles, SC-RPN achieves AR1000 14.5% higher than that of Region Proposal Network (RPN), surpassing all the existing region proposal approaches. We also integrate SC-RPN into Fast R-CNN and Faster R-CNN to test its effectiveness on object detection task, the experimental results achieve a gain of 3.2% and 3.8% in terms of mAP compared to the original ones.

/pdf/sc-rpn-a-strong-correlation-learning-framework-for-region-48v43iidqm.pdf

SC-RPN: A Strong Correlation Learning Framework for Region Proposal

RGB-D Gate-guided edge distillation for indoor semantic segmentation

Recently, with additional information in the disparity variant, quality enhancement for stereo images has become an active research field. Current methods generally adopt cost volumes for stereo matching methods to learn correspondence between stereo image pairs. However, with the large disparity in the different viewpoints of stereo images, how to learn the accurate corresponding information remains a challenge. In addition, as the network deepens, traditional convolutional neural networks (CNNs) adopt cascading methods, which results in the high computational cost and memory consumption. In this paper, we propose an end-to-end effective CNN model. Channel-wise attention-based information distillation and long short-term memory (LSTM) are the basic components, which contribute to reconstruct high quality image (DCL network). Within a stereo image pair, we use high quality (HQ) image to guide the image reconstruction of low quality (LQ). To incorporate the stereo correspondence, information fusion-based LSTM module can be used to learn the disparity variant in stereo images. Specially, in order to distill and enhance effective features map, we introduce channel-wise attention-based a long distillation information module with the consideration of interdependencies among feature channels. Experimental results demonstrate that the proposed network achieves the best performance with comparatively less parameters.

Yingqing Peng

Papers

SC-RPN: A Strong Correlation Learning Framework for Region Proposal

RGB-D Gate-guided edge distillation for indoor semantic segmentation

An Efficient Quality Enhancement Solution for Stereo Images