Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

Bai, 2017, Text/non-text image classification in the wild with convolutional neural networks, Pattern Recogn., 66, 437, 10.1016/j.patcog.2016.12.005 Shi, 2018, Pairwise based deep ranking hashing for histopathology image classification and retrieval, Pattern Recogn., 81, 14, 10.1016/j.patcog.2018.03.015 Zhou, 2018, Deep super-class learning for long-tail distributed image classification, Pattern Recogn., 80, 118, 10.1016/j.patcog.2018.03.003 Krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, 1097 He, 2016, Deep residual learning for image recognition, 770 Krizhevsky, 2009, Learning multiple layers of features from tiny images He, 2016, Identity mappings in deep residual networks, 630 Szegedy, 2017, Inception-v4, Inception-Resnet and the impact of residual connections on learning, 4278 Zhao, 2017, Pyramid scene parsing network, 6230 Russakovsky, 2015, ImageNet Large Scale Visual Recognition Challenge, Int. J. Comput. Vision, 115, 211, 10.1007/s11263-015-0816-y Veit, 2016, Residual networks behave like ensembles of relatively shallow networks, 550 Dai, 2016, Instance-aware semantic segmentation via multi-task network cascades, 3150 Chen, 2017, Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs, IEEE Trans. Pattern Anal. Mach. Intell., 40, 834, 10.1109/TPAMI.2017.2699184 Simonyan, 2015, Very deep convolutional networks for large-scale image recognition Zagoruyko, 2016, Wide residual networks, 87.1 Long, 2017, Fully convolutional networks for semantic segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 39, 640, 10.1109/TPAMI.2016.2572683 Ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, 37, 448 Nair, 2010, Rectified linear units improve restricted boltzmann machines, 807 Peng, 2018, MegDet: A large mini-batch object detector Lin, 2014, Microsoft COCO: Common objects in context, 740 Ren, 2015, Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Trans. Pattern Anal. Mach. Intell., 39, 1137, 10.1109/TPAMI.2016.2577031 Chen, 2016, MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems S. Gross, M. Wilber, Training and investigating residual nets, 2016, (http://torch.ch/blog/2016/02/04/resnets.html). Mishkin, 2017, Systematic evaluation of CNN advances on the ImageNet, Comp. Vis. Image Understanding, 161, 11, 10.1016/j.cviu.2017.05.007 Chen, 2015, Semantic image segmentation with deep convolutional nets and fully connected CRFs J. Wu, C.-W. Xie, J.-H. Luo, Dense CNN learning with equivalent mappings, 2016, (CoRR abs/1605.07251). Everingham, 2015, The PASCAL visual object classes challenge: A retrospective, Int. J. Comput. Vision, 111, 98, 10.1007/s11263-014-0733-5 Srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15, 1929 Z. Wu, C. Shen, A. van den Hengel, Bridging category-level and instance-level semantic image segmentation, 2016, (CoRR abs/1605.06885). Hariharan, 2011, Semantic contours from inverse detectors, 991 Zhou, 2018, Places: A 10 million image database for scene understanding, IEEE Trans. Pattern Anal. Mach. Intell., 40, 1452, 10.1109/TPAMI.2017.2723009 L.-C. Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking atrous convolution for semantic image segmentation, 2017, (CoRR abs/1706.05587). Zheng, 2015, Conditional random fields as recurrent neural networks, 1529 Noh, 2015, Learning deconvolution network for semantic segmentation, 1520 Liu, 2015, Semantic image segmentation via deep parsing network, 1377 Lin, 2017, Exploring context with deep structured models for semantic segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 40, 1352, 10.1109/TPAMI.2017.2708714 Cordts, 2016, The Cityscapes dataset for semantic urban scene understanding, 3213 Zhou, 2017, Scene parsing through ADE20K dataset, 5122 Yu, 2016, Multi-scale context aggregation by dilated convolutions Ghiasi, 2016, Laplacian pyramid reconstruction and refinement for semantic segmentation, 519 Mottaghi, 2014, The role of context for object detection and semantic segmentation in the wild, 891 Dai, 2015, BoxSup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation, 1635