Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
Hefei University of Technology（合肥工业大学）；Soochow University（苏州大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；South China Normal University（华南师范大学）；University of Science and Technology of China（中国科学技术大学）
Zhao Zhang, Zemin Tang, Yang Wang, Zheng Zhang, Choujun Zhan, Zhengjun Zha, Meng Wang
备注：
Please cite this work as: Zhao Zhang, Zemin Tang, Yang Wang, Zheng Zhang, Choujun Zhan, Zhengjun Zha and Meng Wang, "Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition," Neural Networks (NN), Feb 2021. arXiv admin note: text overlap with arXiv:1912.07016
Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Networks (DenseNet), have achieved great success for image representation by discovering deep hierarchical information. However, most existing networks simply stacks the convolutional layers and hence failing to fully discover local and global feature information among layers. In this paper, we mainly explore how to enhance the local and global dense feature flow by exploiting hierarchical features fully from all the convolution layers. Technically, we propose an efficient and effective CNN framework, i.e., Fast Dense Residual Network (FDRN), for text recognition. To construct FDRN, we propose a new fast residual dense block (f-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts at the same time. After fully learning local residual dense features, we utilize the sum operation and several f-RDBs to define a new block termed global dense block (GDB) by imitating the construction of dense blocks to learn global dense residual features adaptively in a holistic way. Finally, we use two convolution layers to construct a down-sampling block to reduce the global feature size and extract deeper features. Extensive simulations show that FDRN obtains the enhanced recognition results, compared with other related models.
Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）；Center for Long-term Artificial Intelligence（长期人工智能中心）；Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Chinese Academy of Sciences（中国科学院脑认知与脑智能技术重点实验室）
Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images
SpineMamba: Enhancing 3D Spinal Segmentation in Clinical Imaging through Residual Visual Mamba Layers and Shape Priors
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Northeast Petroleum University（东北石油大学）；Northeastern University（东北大学）；Southern Medical University（南方医科大学）
Enhancing mTBI Diagnosis with Residual Triplet Convolutional Neural Network Using 3D CT
School of Electrical Engineering and Computer Science, University of Queensland（昆士兰大学电气工程与计算机科学学院）；The Centre for Advanced Imaging, Australian Institute for Bioengineering and Nanotechnology, University of Queensland（昆士兰大学高级成像中心，澳大利亚生物工程与纳米技术研究所）；ARC Training Centre for Innovation in Biomedical Imaging Technology（ARC生物医学成像技术创新培训中心）
RES-SE-NET: Boosting Performance of Resnets by Enhancing Bridge-connections
Sri Sathya Sai Institute of Higher Learning（斯里萨蒂亚赛高等教育学院）；Department of Mathematics and Computer Science（数学与计算机科学系）；Prasanthi Nilayam, AP, India（普拉萨蒂尼莱亚姆，安得拉邦，印度）
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
卷积神经网络（CNN）已被视为一类强大的模型，用于图像识别问题。然而，当利用CNN来学习时空视频表示时，这并非微不足道。一些研究表明，执行3D卷积是捕获视频中空间和时间维度的有益方法。然而，从头开始开发非常深的3D CNN导致昂贵的计算成本和存储器需求。一个有效的问题是为什么不将现成的2D网络回收用于3D CNN。在本文中，我们通过在空间域（相当于2D CNN）上使用$1\times3\times3$卷积滤波器模拟$3\times3\times3$卷积加上$3\times1\times1$卷积来构建时间上相邻特征映射的时间连接，从而在残差学习框架中设计了瓶颈构建块的多种变体。此外，我们提出了一种新的架构，称为伪三维残差网络（P3 D ResNet），它利用了块的所有变体，但将每个变体组合在ResNet的不同位置，遵循的理念是，通过深入增强结构多样性可以提高神经网络的能力。我们的P3 D ResNet在Sports-1 M视频分类数据集上对3D CNN和基于帧的2D CNN分别实现了5.3%和1.8%的明显改进。我们进一步研究了预训练的P3 D ResNet在五个不同的基准测试和三个不同的任务上产生的视频表示的泛化性能，证明了优于几种最先进技术的性能。
Adaptive Residual Transformation for Enhanced Feature-Based OOD Detection in SAR Imagery
Next Generation Defence Multidisciplinary Technology Research Center, Pohang University of Science and Technology（浦项科技大学下一代国防多学科技术研究中心）；Pohang University of Science and Technology（浦项科技大学）
