Attention-Aware Noisy Label Learning for Image Classification

Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision, such as image/video classification. The cheapest way to obtain a large body of labeled visual data is to crawl from websites with user-supplied labels, such as Flickr. However, these samples often tend to contain incorrect labels (i.e. noisy labels), which will significantly degrade the network performance. In this paper, the attention-aware noisy label learning approach ($A^2NL$) is proposed to improve the discriminative capability of the network trained on datasets with potential label noise. Specifically, a Noise-Attention model, which contains multiple noise-specific units, is designed to better capture noisy information. Each unit is expected to learn a specific noisy distribution for a subset of images so that different disturbances are more precisely modeled. Furthermore, a recursive learning process is introduced to strengthen the learning ability of the attention network by taking advantage of the learned high-level knowledge. To fully evaluate the proposed method, we conduct experiments from two aspects: manually flipped label noise on large-scale image classification datasets, including CIFAR-10, SVHN; and real-world label noise on an online crawled clothing dataset with multiple attributes. The superior results over state-of-the-art methods validate the effectiveness of our proposed approach.

[1]  Hanqing Lu,et al.  BundleNet: Learning with Noisy Label via Sample Correlations , 2018, IEEE Access.

[2]  Jian Yang,et al.  SRNN: Self-regularized neural network , 2018, Neurocomputing.

[3]  A. Krizhevsky Convolutional Deep Belief Networks on CIFAR-10 , 2010 .

[4]  Rich Caruana,et al.  Model compression , 2006, KDD '06.

[5]  Kristen Grauman,et al.  Zero-shot recognition with unreliable attributes , 2014, NIPS.

[6]  Raja Giryes,et al.  On the Resistance of Neural Nets to Label Noise , 2018, ArXiv.

[7]  Jason Weston,et al.  Deep learning via semi-supervised embedding , 2008, ICML '08.

[8]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[9]  Gang Wang,et al.  Multi-Task CNN Model for Attribute Prediction , 2015, IEEE Transactions on Multimedia.

[10]  Qingming Huang,et al.  Robust Latent Poisson Deconvolution From Multiple Features for Web Topic Detection , 2016, IEEE Transactions on Multimedia.

[11]  Matthew S. Nokleby,et al.  Learning Deep Networks from Noisy Labels with Dropout Regularization , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[12]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[13]  Kiyoharu Aizawa,et al.  Joint Optimization Framework for Learning with Noisy Labels , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Lance Chun Che Fung,et al.  Data Cleaning for Classification Using Misclassification Analysis , 2010, J. Adv. Comput. Intell. Intell. Informatics.

[15]  Jian Zhang,et al.  Exploiting Web Images for Dataset Construction: A Domain Robust Approach , 2016, IEEE Transactions on Multimedia.

[16]  Yale Song,et al.  Learning from Noisy Labels with Distillation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Mert R. Sabuncu,et al.  Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels , 2018, NeurIPS.

[18]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[19]  Xiaogang Wang,et al.  Learning from massive noisy labeled data for image classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Jacob Goldberger,et al.  Training deep neural-networks using a noise adaptation layer , 2016, ICLR.

[21]  Rob Fergus,et al.  Learning from Noisy Labels with Deep Neural Networks , 2014, ICLR.

[22]  Le Song,et al.  Iterative Learning with Open-set Noisy Labels , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Qiang Chen,et al.  Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[24]  Xin Liu,et al.  Self-Error-Correcting Convolutional Neural Network for Learning with Noisy Labels , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[25]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[26]  Ata Kabán,et al.  Boosting in the presence of label noise , 2013, UAI.

[27]  Yangqing Jia,et al.  Deep Convolutional Ranking for Multilabel Image Annotation , 2013, ICLR.