CNN Papers
文章平均质量分 74
Hao_Zhang_Vision
这个作者很懒,什么都没留下…
展开
-
[深度学习论文笔记] Convolutional Neuron Networks and its Applications
In artificial intelligence, there exists a Moravec’s Paradox, 1 “High-level reasoning requires very little computation, but low-level sensorimotor skills require enormous computational resources”. It原创 2016-11-19 11:11:23 · 1318 阅读 · 0 评论 -
[深度学习论文笔记][Object Detection] You Only Look Once: Unified, Real-Time Object Detection
Redmon, Joseph, et al. “You only look once: Unified, real-time object detection.” arXiv preprint arXiv:1506.02640 (2015). (Citations: 76).1 MotivationWe frame object detection as a regression原创 2016-11-12 17:57:04 · 862 阅读 · 0 评论 -
[深度学习论文笔记][Video Classification] Large-scale Video Classification with Convolutional Neural Networks
Karpathy, Andrej, et al. “Large-scale video classification with convolutional neural networks.” Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2014. (Citations: 654).原创 2016-11-16 10:16:32 · 2558 阅读 · 0 评论 -
[深度学习论文笔记][Attention] Spatial Transformer Networks
Jaderberg, Max, Karen Simonyan, and Andrew Zisserman. “Spatial transformer networks.” Advances in Neural Information Processing Systems. 2015. (Citations: 116).1 MotivationThe Show, Attend and原创 2016-11-15 22:02:11 · 3072 阅读 · 0 评论 -
[深度学习论文笔记][Attention]Show, Attend, and Tell: Neural Image Caption Generation with Visual Attention
Xu, Kelvin, et al. “Show, attend and tell: Neural image caption generation with visual attention.” arXiv preprint arXiv:1502.03044 2.3 (2015): 5. (Citations: 401).1 MotivationIn the previous i原创 2016-11-15 19:53:02 · 6117 阅读 · 0 评论 -
[深度学习论文笔记][Neural Arts] Inceptionism: Going Deeper into Neural Networks
Mordvintsev, Alexander, Christopher Olah, and Mike Tyka. “Inceptionism: Going deeper into neural networks.” Google Research Blog. Retrieved June 20 (2015). (Citations: 36).1 MotivationEach lay原创 2016-10-31 11:02:19 · 1193 阅读 · 0 评论 -
[深度学习论文笔记][Image Reconstruction] Understanding Deep Image Representations by Inverting Them
Mahendran, Aravindh, and Andrea Vedaldi. “Understanding deep image representations by inverting them.” 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, 2015. (Citations:原创 2016-10-31 10:07:51 · 3188 阅读 · 0 评论 -
[深度学习论文笔记][Visualizing] Understanding Neural Networks Through Deep Visualization
Yosinski, Jason, et al. “Understanding neural networks through deep visualization.” arXiv preprint arXiv:1506.06579 (2015). (Citations: 65).1 Optimization For Any Arbitary Neuron2 Thre原创 2016-10-31 08:27:33 · 1259 阅读 · 0 评论 -
[深度学习论文笔记][Object Detection] Faster R-CNN: Towards Real-Time Object
Ren, Shaoqing, et al. “Faster R-CNN: Towards real-time object detection with region proposal networks.” Advances in neural information processing systems. 2015. (Citations:444).1 MotivationR原创 2016-11-10 21:14:22 · 1018 阅读 · 0 评论 -
[深度学习论文笔记][Object Detection] Fast R-CNN
Girshick, Ross. “Fast r-cnn.” Proceedings of the IEEE International Conference on Computer Vision. 2015. (Citations: 444).1 R-CNN Problems• Slow at test-time: need to run full forward pass of原创 2016-11-10 15:16:14 · 665 阅读 · 0 评论 -
[深度学习论文笔记][Visualizing] 网络可视化部分论文导读
There are several ways to understanding and visualing CNN1 Visualizing ActivationsShow the activations of the network during the forward pass. It turns out that the activations usually start o原创 2016-10-29 10:19:07 · 1040 阅读 · 0 评论 -
[深度学习论文笔记][Visualizing] Striving for Simplicity: The All Convolutional Net
Springenberg, Jost Tobias, et al. “Striving for simlicity: The all convolutional net.” arXiv preprint arXiv:1412.6806 (2014). (Citations: 121).1 Deconv Approach (Guided Backpropagation)It comb原创 2016-10-29 10:16:48 · 1721 阅读 · 0 评论 -
[深度学习论文笔记][Visualizing] Deep Inside Convolutional Networks Visualising Image Classification
Simonyan, Karen, Andrea Vedaldi, and Andrew Zisserman. “Deep inside convolutional networks: Visualising image classification models and saliency maps.” arXiv preprint arXiv:1312.6034 (2013). (Citation原创 2016-10-27 15:12:32 · 3664 阅读 · 0 评论 -
[深度学习论文笔记][Semantic Segmentation] Learning Hierarchical Features for Scene Labeling
Farabet, Clement, et al. “Learning hierarchical features for scene labeling.” IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1915-1929. (Citations:703).1 Pipeline原创 2016-11-12 18:33:09 · 726 阅读 · 0 评论 -
[深度学习论文笔记][Neural Arts] A Neural Algorithm of Artistic Style
Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. “A neural algorithm of artistic style.” arXiv preprint arXiv:1508.06576 (2015). (Citations: 99).1 MotivationGiven a content image and a原创 2016-11-01 09:24:14 · 960 阅读 · 0 评论 -
[深度学习论文笔记][Video Classification] Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, Du, et al. “Learning spatiotemporal features with 3d convolutional networks.” 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 2015. (Citations: 101).1 ArchitectureThi原创 2016-11-16 11:04:09 · 1947 阅读 · 0 评论 -
[深度学习论文笔记][Image to Sentence Generation] Deep Visual-Semantic Alignments for Generating Image Descri
Karpathy, Andrej, and Li Fei-Fei. “Deep visual-semantic alignments for generating image descriptions.” Proceedings of the IEEE Conference on Computer Vision and PatternRecognition. 2015. (Citations:原创 2016-11-14 21:29:18 · 1607 阅读 · 0 评论 -
[深度学习论文笔记][Video Classification] Delving Deeper into Convolutional Networks for Learning Video Repre
Ballas, Nicolas, et al. “Delving Deeper into Convolutional Networks for Learning Video Representations.” arXiv preprint arXiv:1511.06432 (2015). (Citaions: 14).1 MotivationPrevious works on Re原创 2016-11-17 16:01:17 · 2170 阅读 · 0 评论 -
[深度学习论文笔记][Recurrent Neural Networks] Visualizing and Understanding Recurrent Networks
Karpathy, Andrej, Justin Johnson, and Li Fei-Fei. “Visualizing and understanding recurrent networks” arXiv preprint arXiv:1506.02078 (2015). (Citations: 79).1 RNNRNN has formWhere W vari原创 2016-11-14 15:15:59 · 1293 阅读 · 0 评论 -
[深度学习论文笔记][Video Classification] Beyond Short Snippets: Deep Networks for Video Classification
Yue-Hei Ng, Joe, et al. “Beyond short snippets: Deep networks for video classification.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. (Citations: 171).1 A原创 2016-11-17 14:57:26 · 3276 阅读 · 0 评论 -
[深度学习论文笔记][Video Classification] Long-term Recurrent Convolutional Networks for Visual Recognition a
Donahue, Jeffrey, et al. ”Long-term recurrent convolutional networks for visual recognition and description.” Proceedings of the IEEE Conference on Computer Vision and PatternRecognition. 2015. (Cit原创 2016-11-17 11:06:12 · 1771 阅读 · 1 评论 -
[深度学习论文笔记][Video Classification] Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, Karen, and Andrew Zisserman. “Two-stream convolutional networks for action recognition in videos.” Advances in Neural Information Processing Systems. 2014.(Citations: 425).1 Motivati原创 2016-11-17 09:27:36 · 1989 阅读 · 0 评论 -
[深度学习论文笔记][Instance Segmentation] Instance-aware Semantic Segmentation via Multi-task Network Cascad
Dai, Jifeng, Kaiming He, and Jian Sun. “Instance-aware semantic segmentation via multitask network cascades.” arXiv preprint arXiv:1512.04412 (2015). (Citations: 40).1 MotivationAll previous w原创 2016-11-13 20:12:25 · 2125 阅读 · 1 评论 -
[深度学习论文笔记][Instance Segmentation] Hypercolumns for Object Segmentation and Fine-Grained Localization
Hariharan, Bharath, et al. “Hypercolumns for object segmentation and fine-grained localization.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recogni-tion. 2015. (Citations: 185原创 2016-11-13 19:01:25 · 3295 阅读 · 0 评论 -
[深度学习论文笔记][Instance Segmentation] Simultaneous Detection and Segmentation
Hariharan, Bharath, et al. “Simultaneous detection and segmentation.” European Conference on Computer Vision. Springer International Publishing, 2014. (Citations: 234).1 PipelineSee Fig. The i原创 2016-11-13 16:41:08 · 2764 阅读 · 0 评论 -
[深度学习论文笔记][Semantic Segmentation] Learning Deconvolution Network for Semantic Segmentation
Noh, Hyeonwoo, Seunghoon Hong, and Bohyung Han. “Learning deconvolution network for semantic segmentation.” Proceedings of the IEEE International Conference on Com-puter Vision. 2015. (Citations: 13原创 2016-11-13 15:41:55 · 1090 阅读 · 0 评论 -
[深度学习论文笔记][Semantic Segmentation] Fully Convolutional Networks for Semantic Segmentation
Long, Jonathan, Evan Shelhamer, and Trevor Darrell. “Fully convolutional networks for semantic segmentation.” Proceedings of the IEEE Conference on Computer Vision andPattern Recognition. 2015. (Cit原创 2016-11-13 14:46:12 · 1119 阅读 · 0 评论 -
[深度学习论文笔记][Semantic Segmentation] Recurrent Convolutional Neural Networks for Scene Labeling
Pinheiro, Pedro HO, and Ronan Collobert. “Recurrent Convolutional Neural Networks for Scene Labeling.” ICML. 2014. (Citations: 163).1 PipelineSee Fig. Each instance takes as input both an resi原创 2016-11-12 19:43:13 · 1473 阅读 · 1 评论 -
[深度学习论文笔记][Object Detection] Rich feature hierarchies for accurate object detection and semantic seg
Girshick, Ross, et al. “Rich feature hierarchies for accurate object detection and semantic segmentation.” Proceedings of the IEEE conference on computer vision and patternrecognition. 2014. (Citati原创 2016-11-09 18:36:32 · 620 阅读 · 0 评论 -
[深度学习论文笔记][Depth Estimation] Predicting Depth, Surface Normals and Semantic Labels with a Common M
Eigen, David, and Rob Fergus. “Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture.” Proceedings of the IEEE International Conference on Computer原创 2016-10-18 17:32:35 · 2316 阅读 · 0 评论 -
[深度学习论文笔记][Weight Initialization] All you need is a good init
Mishkin, Dmytro, and Jiri Matas. “All you need is a good init.” arXiv preprint arXiv:1511.06422 (2015). [Citations: 19].1 Layer-Sequential Unit-Variance Initialization[Idea]• Pre-initialize原创 2016-09-22 09:39:34 · 2275 阅读 · 0 评论 -
[深度学习论文笔记][Image Classification] Very Deep Convolutional Networks for Large-Scale Image Recognitio
Simonyan, Karen, and Andrew Zisserman. “Very deep convolutional networks for large-scale image recognition.” arXiv preprint arXiv:1409.1556 (2014). [Citations: 1986].1 Motivation[Ways to Impro原创 2016-09-25 16:07:15 · 773 阅读 · 0 评论 -
[深度学习论文笔记][Image Classification] 图像分类部分论文导读
[ImageNet]• Over 15M labeled high resolution images.• Roughly 22k categories.• Collected from web and labeled by Amazon Mechanical Turk.[ILSVRC (ImageNet Large-Scale Visual Recognition Cha原创 2016-10-11 08:44:11 · 2444 阅读 · 0 评论 -
[深度学习论文笔记][Weight Initialization] Understanding the difficulty of training deep feedforward neural
Glorot, Xavier, and Yoshua Bengio. “Understanding the difficulty of training deep feedforward neural networks.” Aistats. Vol. 9. 2010. [Citations: 722].1.1.1 Cost Function SurfacePlateaus are原创 2016-09-20 08:21:23 · 1347 阅读 · 4 评论 -
[深度学习论文笔记][Weight Initialization] Exact solutions to the nonlinear dynamics of learning in deep lin
Saxe, Andrew M., James L. McClelland, and Surya Ganguli. “Exact solutions to the nonlinear dynamics of learning in deep linear neural net-works.” arXiv preprint arXiv:1312.6120 (2013). [Citations: 9原创 2016-09-20 09:58:36 · 1159 阅读 · 0 评论 -
[深度学习论文笔记][Weight Initialization] Random walk initialization for training very deep feedforward netw
Sussillo, David, and L. F. Abbott. “Random walk initialization for training very deep feedforward networks.” arXiv preprint arXiv:1412.6558 (2014). [Citations: 3].1.3.1 Motivation[Motivation]原创 2016-09-20 10:08:27 · 1164 阅读 · 0 评论 -
[深度学习论文笔记][Weight Initialization] Batch Normalization: Accelerating Deep Network Training by Reducin
Ioffe, Sergey, and Christian Szegedy. “Batch normalization: Accelerating deep network training by reducing internal covariate shift.” arXiv preprint arXiv:1502.03167 (2015). [Citations: 532].1 M原创 2016-09-20 13:54:38 · 1294 阅读 · 0 评论 -
[深度学习论文笔记][Weight Initialization] Delving deep into rectifiers: Surpassing human-level performance
He, Kaiming, et al. “Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.” Proceedings of the IEEE International Conference on Computer Vision. 2015. [Citations原创 2016-09-20 17:21:26 · 1566 阅读 · 0 评论 -
[深度学习论文笔记][Weight Initialization] Data-dependent Initializations of Convolutional Neural Networks
Krhenbhl, Philipp, et al. “Data-dependent initializations of convolutional neural networks.” arXiv preprint arXiv:1511.06856 (2015). [Citations: 10].1 Attenuating Activations[Idea] Initialize原创 2016-09-21 14:25:59 · 1287 阅读 · 0 评论 -
[深度学习论文笔记][Image Classification] Deep Residual Learning for Image Recognition
He, Kaiming, et al. “Deep residual learning for image recognition.” arXiv preprint arXiv:1512.03385 (2015). [Citations: 525].1 Is Learning Better Networks as Easy as Stacking More Layers?[Vani原创 2016-10-10 10:06:25 · 851 阅读 · 0 评论