Walking on Two Legs: Learning Image Segmentation with Noisy Labels

Image segmentation automatically segments a target object in an image and has recently achieved prominent progress due to the development of deep convolutional neural networks (DCNNs). However, the quality of manual labels plays an essential role in the segmentation accuracy, while in practice it could vary a lot and in turn could substantially mislead the training process and limit the effectiveness. In this paper, we propose a novel label refinement and sample reweighting method, and a novel generative adversarial network (GAN) is introduced to fuse these two models into an integrated framework. We evaluate our approach on the publicly available datasets, and the results show our approach to be competitive when compared with other state-of-the-art approaches dealing with the noisy labels in image segmentation.

[1]  Yizhou Yu,et al.  Traffic Sign Detection Using a Multi-Scale Recurrent Attention Network , 2019, IEEE Transactions on Intelligent Transportation Systems.

[2]  Chao Song,et al.  Joint temporal context exploitation and active learning for video segmentation , 2020, Pattern Recognit..

[3]  Chengle Zhou,et al.  Hyperspectral Classification With Noisy Label Detection via Superpixel-to-Pixel Weighting Distance , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Hao Lu,et al.  Indices Matter: Learning to Index for Deep Image Matting , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[5]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jan Kautz,et al.  Learning Affinity via Spatial Propagation Networks , 2017, NIPS.

[7]  Xiaogang Wang,et al.  Learning Object Interactions and Descriptions for Semantic Image Segmentation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[9]  Xun Wang,et al.  Object localization via evaluation multi-task learning , 2017, Neurocomputing.

[10]  Haibin Ling,et al.  A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Lei Zhang,et al.  CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Xun Wang,et al.  Lane marking detection via deep convolutional neural network , 2017, Neurocomputing.

[13]  Hong Qiao,et al.  Un-supervised and semi-supervised hand segmentation in egocentric images with noisy label learning , 2019, Neurocomputing.

[14]  Jian Sun,et al.  Learnable Tree Filter for Structure-preserving Feature Transform , 2019, NeurIPS.

[15]  Tatsuya Harada,et al.  Multi-Stage Pathological Image Classification Using Semantic Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Shadi Albarqouni,et al.  Learn to Estimate Labels Uncertainty for Quality Assurance , 2019, ArXiv.

[17]  Takuhiro Kaneko,et al.  Label-Noise Robust Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Siniša Šegvić,et al.  In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Stella X. Yu,et al.  Adaptive Affinity Fields for Semantic Segmentation , 2018, ECCV.

[20]  Yan Tian,et al.  Multi-scale Hierarchical Residual Network for Dense Captioning , 2019, J. Artif. Intell. Res..

[21]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[22]  Wei Hu,et al.  Densely connected attentional pyramid residual network for human pose estimation , 2019, Neurocomputing.

[23]  Peng Jiang,et al.  DifNet: Semantic Segmentation by Diffusion Networks , 2018, NeurIPS.

[24]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

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

[27]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[29]  Huchuan Lu,et al.  Deep gated attention networks for large-scale street-level scene segmentation , 2019, Pattern Recognit..

[30]  Zhiwei Wang,et al.  Label Refinement with an Iterative Generative Adversarial Network for Boosting Retinal Vessel Segmentation. , 2019 .