深度学习 适合用来做少样本的分类么?

综合问题moyan 发表了文章 • 3 个评论 • 915 次浏览 • 2016-12-29 17:46 • 来自相关话题

手头上有一批样本 有1000个样本,分6类,其中某一类总共才100个样本(各类样本数量很不均衡),各类取30%来测试,用的是alexnet,目前的分类精度才40%,请各位大神指点一下,对于这种少样本且不均衡的数据怎么来做分类。
手头上有一批样本 有1000个样本,分6类,其中某一类总共才100个样本(各类样本数量很不均衡),各类取30%来测试,用的是alexnet,目前的分类精度才40%,请各位大神指点一下,对于这种少样本且不均衡的数据怎么来做分类。

训练时样本有什么要求?

图像分类陶潜水 回复了问题 • 2 人关注 • 2 个回复 • 68 次浏览 • 3 天前 • 来自相关话题

LeNet能否识别普通的图片

深度学习应用Fantasysoda 回复了问题 • 2 人关注 • 2 个回复 • 82 次浏览 • 3 天前 • 来自相关话题

感受野具体是什么意思

综合问题joshua_1988 回复了问题 • 2 人关注 • 1 个回复 • 62 次浏览 • 3 天前 • 来自相关话题

caffe自己训练好模型,用python接口测试训练时的测试数据集,和训练时得到的accuracy差距很大

回复

人脸识别wjschsg88 发起了问题 • 1 人关注 • 0 个回复 • 74 次浏览 • 4 天前 • 来自相关话题

怎样在caffe上训练时使用交叉验证

回复

综合问题COCO_1 发起了问题 • 1 人关注 • 0 个回复 • 65 次浏览 • 4 天前 • 来自相关话题

21天实战Caffe windows系统情况下的编译问题

Caffe环境安装shakevincent 回复了问题 • 2 人关注 • 1 个回复 • 81 次浏览 • 4 天前 • 来自相关话题

比较一下Lenet,AlexNet,Cifar10网络的不同

深度学习应用匿名用户 回复了问题 • 2 人关注 • 2 个回复 • 52 次浏览 • 5 天前 • 来自相关话题

argmax gpu实现

回复

Caffe开发使用Webber 发起了问题 • 1 人关注 • 0 个回复 • 47 次浏览 • 5 天前 • 来自相关话题

神经网络识别图片分辨率有什么要求?

回复

目标识别mhaoyang 发起了问题 • 1 人关注 • 0 个回复 • 67 次浏览 • 5 天前 • 来自相关话题

caffe有upsample吗?

目标识别c408550969 回复了问题 • 3 人关注 • 3 个回复 • 81 次浏览 • 5 天前 • 来自相关话题

制作hdf5文件文件

回复

综合问题数学爱好者26 发起了问题 • 1 人关注 • 0 个回复 • 55 次浏览 • 5 天前 • 来自相关话题

caffe中name和top的问题

回复

深度学习理论c408550969 发起了问题 • 1 人关注 • 0 个回复 • 55 次浏览 • 5 天前 • 来自相关话题

CaffeCN推荐阅读论文列表

论文阅读caffe 发表了文章 • 11 个评论 • 4661 次浏览 • 2016-01-18 11:46 • 来自相关话题

更新:
CaffeCN社区开辟了论文主题站,定期更新各领域最新的重要论文,http://paper.caffecn.cn/
欢迎各位到论文主题站推荐论文,如果您对某篇论文有疑惑,也欢迎您在各论文的主题下提问和讨论。
 
CaffeCN推荐阅读论文列表(持续更新中 20160131)

1.理论
1.1 综述
Lecun Y, Bengio Y, Hinton G. Deep learning.[J]. Nature, 2015, 521(7553):436-44.Schmidhuber J. Deep learning in neural networks: An overview[J]. Neural Networks, 2015, 61: 85-117.
1.2 数学基础
K. B. Petersen and M. S. Pedersen, “The matrix cookbook,” nov 2012, Version 20121115.
 
1.3 收敛理论
Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks[C]//International conference on artificial intelligence and statistics. 2010: 249-256.Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[J]. arXiv preprint arXiv:1502.03167, 2015.Neyshabur B, Salakhutdinov R R, Srebro N. Path-sgd: Path-normalized optimization in deep neural networks[C]//Advances in Neural Information Processing Systems. 2015: 2413-2421.
 
2. 模型
2.1 CNN
Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. 2012: 1097-1105.Szegedy C, Liu W, Jia Y, et al. Going Deeper With Convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 1-9.Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.Srivastava R K, Greff K, Schmidhuber J. Highway Networks[J]. arXiv preprint arXiv:1505.00387, 2015.

2.2 RNN
Graves A. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735-1780.Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005, 18(s 5–6):602-610.Chung J, Gulcehre C, Cho K H, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[J]. Eprint Arxiv, 2014.

3.应用
 
3.1 图像分类
Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. 2012: 1097-1105.He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[J]. arXiv preprint arXiv:1512.03385, 2015.Kontschieder P, Fiterau M, Criminisi A, et al. Deep Neural Decision Forests[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 1467-1475.(ICCV2015 Marr Prize)Joint Embeddings of Shapes and Images via CNN Image Purification ACM Transactions on Graphics (Proceeding of SIGGRAPH Asia 2015)
 
3.2 人脸识别
Taigman Y, Yang M, Ranzato M, Wolf L. Deepface: Closing the gap to human-level performance in face verification. In: Computer Vision and Pattern Recognition (CVPR). 2014 Sun Y, Wang X, Tang X. Deep learning face representation from predicting 10,000 classes. In: Computer Vision and Pattern Recognition (CVPR). 2014, 1891–1898 Sun Y, Chen Y, Wang X, Tang X. Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems (NIPS). 2014, 1988–1996Sun Y, Wang X, Tang X. Deeply learned face representations are sparse, selective, and robust. arXiv preprint arXiv:1412.1265, 2014Yi D, Lei Z, Liao S, Li S Z. Learning face representation from scratch. arXiv preprint arXiv:1411.7923, 2014 Schroff F, Kalenichenko D, Philbin J. Facenet: A unified embedding for face recognition and clustering. arXiv preprint arXiv:1503.03832, 2015

3.3 目标检测
Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems. 2015: 91-99.Girshick R. Fast R-CNN[J]. arXiv preprint arXiv:1504.08083, 2015.(ICCV2015)Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014: 580-587.Hosang J, Benenson R, Dollár P, et al. What makes for effective detection proposals[J]. arXiv preprint arXiv:1502.05082, 2015.(TPAMI2015)Yoo D, Park S, Lee J Y, et al. AttentionNet: Aggregating Weak Directions for Accurate Object Detection[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 2659-2667.

3.4 OCR
Graves A, Schmidhuber J. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks.[J]. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks. - ResearchGate, 2008:545-552.

3.5 图像描述
Donahue J, Hendricks L A, Guadarrama S, et al. Long-term recurrent convolutional networks for visual recognition and description[C]// Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on. IEEE, 2015.

 3.6 动作识别
Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[C]//Advances in Neural Information Processing Systems. 2014: 568-576.


================================================
说明:本列表由CaffeCN社区(caffecn.cn)答疑组共同整理,仅提供给CaffeCN社区使用,如需转载须注明转载来源。
================================================  查看全部
更新
CaffeCN社区开辟了论文主题站,定期更新各领域最新的重要论文,http://paper.caffecn.cn/
欢迎各位到论文主题站推荐论文,如果您对某篇论文有疑惑,也欢迎您在各论文的主题下提问和讨论。
 
CaffeCN推荐阅读论文列表(持续更新中 20160131)

1.理论
1.1 综述
  • Lecun Y, Bengio Y, Hinton G. Deep learning.[J]. Nature, 2015, 521(7553):436-44.
  • Schmidhuber J. Deep learning in neural networks: An overview[J]. Neural Networks, 2015, 61: 85-117.

1.2 数学基础
  • K. B. Petersen and M. S. Pedersen, “The matrix cookbook,” nov 2012, Version 20121115.

 
1.3 收敛理论
  • Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks[C]//International conference on artificial intelligence and statistics. 2010: 249-256.
  • Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[J]. arXiv preprint arXiv:1502.03167, 2015.
  • Neyshabur B, Salakhutdinov R R, Srebro N. Path-sgd: Path-normalized optimization in deep neural networks[C]//Advances in Neural Information Processing Systems. 2015: 2413-2421.

 
2. 模型
2.1 CNN
  • Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. 2012: 1097-1105.
  • Szegedy C, Liu W, Jia Y, et al. Going Deeper With Convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 1-9.
  • Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
  • Srivastava R K, Greff K, Schmidhuber J. Highway Networks[J]. arXiv preprint arXiv:1505.00387, 2015.


2.2 RNN
  • Graves A. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735-1780.
  • Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005, 18(s 5–6):602-610.
  • Chung J, Gulcehre C, Cho K H, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[J]. Eprint Arxiv, 2014.


3.应用
 
3.1 图像分类
  • Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. 2012: 1097-1105.
  • He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[J]. arXiv preprint arXiv:1512.03385, 2015.
  • Kontschieder P, Fiterau M, Criminisi A, et al. Deep Neural Decision Forests[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 1467-1475.(ICCV2015 Marr Prize)
  • Joint Embeddings of Shapes and Images via CNN Image Purification ACM Transactions on Graphics (Proceeding of SIGGRAPH Asia 2015)

 
3.2 人脸识别
  • Taigman Y, Yang M, Ranzato M, Wolf L. Deepface: Closing the gap to human-level performance in face verification. In: Computer Vision and Pattern Recognition (CVPR). 2014
  •  Sun Y, Wang X, Tang X. Deep learning face representation from predicting 10,000 classes. In: Computer Vision and Pattern Recognition (CVPR). 2014, 1891–1898
  •  Sun Y, Chen Y, Wang X, Tang X. Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems (NIPS). 2014, 1988–1996
  • Sun Y, Wang X, Tang X. Deeply learned face representations are sparse, selective, and robust. arXiv preprint arXiv:1412.1265, 2014
  • Yi D, Lei Z, Liao S, Li S Z. Learning face representation from scratch. arXiv preprint arXiv:1411.7923, 2014
  •  Schroff F, Kalenichenko D, Philbin J. Facenet: A unified embedding for face recognition and clustering. arXiv preprint arXiv:1503.03832, 2015


3.3 目标检测
  • Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems. 2015: 91-99.
  • Girshick R. Fast R-CNN[J]. arXiv preprint arXiv:1504.08083, 2015.(ICCV2015)
  • Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014: 580-587.
  • Hosang J, Benenson R, Dollár P, et al. What makes for effective detection proposals[J]. arXiv preprint arXiv:1502.05082, 2015.(TPAMI2015)
  • Yoo D, Park S, Lee J Y, et al. AttentionNet: Aggregating Weak Directions for Accurate Object Detection[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 2659-2667.


3.4 OCR
  • Graves A, Schmidhuber J. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks.[J]. Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks. - ResearchGate, 2008:545-552.


3.5 图像描述
  • Donahue J, Hendricks L A, Guadarrama S, et al. Long-term recurrent convolutional networks for visual recognition and description[C]// Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on. IEEE, 2015.


 3.6 动作识别
  • Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[C]//Advances in Neural Information Processing Systems. 2014: 568-576.



================================================
说明:本列表由CaffeCN社区(caffecn.cn)答疑组共同整理,仅提供给CaffeCN社区使用,如需转载须注明转载来源。
================================================ 

caffe生成lmdb文件最大只有32G

回复

深度学习应用liuqingjie1987 发起了问题 • 1 人关注 • 0 个回复 • 73 次浏览 • 2017-08-11 16:24 • 来自相关话题

为什么最近的论文都在追逐小的模型,如squeezeNet,mobileNet....模型的大小带来的好处有哪些?

综合问题辛淼 回复了问题 • 4 人关注 • 3 个回复 • 143 次浏览 • 2017-08-11 11:11 • 来自相关话题

下载的imagenet的train图片不全,txt需不需要修改?

回复

图像分类c408550969 发起了问题 • 1 人关注 • 0 个回复 • 81 次浏览 • 2017-08-11 10:58 • 来自相关话题

ssd目标检测能够检测旋转或倾斜图像吗,如果能有何依据呢,论文中没看到有提及

深度学习应用joshua_1988 回复了问题 • 2 人关注 • 1 个回复 • 86 次浏览 • 2017-08-11 09:03 • 来自相关话题