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。

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