Self Paced Deep Learning for Weakly Supervised Object Detection

In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple Instance Learning framework in which the current classifier is used to select the highest-confidence boxes in each image, which are treated as pseudo-ground truth in the next training iteration. However, the errors of an immature classifier can make the process drift, usually introducing many of false positives in the training dataset. To alleviate this problem, we propose in this paper a training protocol based on the self-paced learning paradigm. The main idea is to iteratively select a subset of images and boxes that are the most reliable, and use them for training. While in the past few years similar strategies have been adopted for SVMs and other classifiers, we are the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline. The method we propose is built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes. We show state-of-the-art results on Pascal VOC 2007, Pascal VOC 2010 and ILSVRC 2013. On ILSVRC 2013 our results based on a low-capacity AlexNet network outperform even those weakly-supervised approaches which are based on much higher-capacity networks.

[1]  Miaojing Shi,et al.  Weakly Supervised Object Localization Using Size Estimates , 2016, ECCV.

[2]  Alexei A. Efros,et al.  Ensemble of exemplar-SVMs for object detection and beyond , 2011, 2011 International Conference on Computer Vision.

[3]  Jitendra Malik,et al.  Contextual Action Recognition with R*CNN , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[5]  T. Tuytelaars,et al.  Weakly Supervised Object Detection with Posterior Regularization , 2014 .

[6]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[7]  Daphne Koller,et al.  Self-Paced Learning for Latent Variable Models , 2010, NIPS.

[8]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[9]  Luc Van Gool,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[10]  Dragomir Anguelov,et al.  Self-taught object localization with deep networks , 2014, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[11]  Yunchao Wei,et al.  Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Deyu Meng,et al.  Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-Paced Curriculum Learning , 2016, IJCAI.

[13]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[14]  Yong Jae Lee,et al.  Learning the easy things first: Self-paced visual category discovery , 2011, CVPR 2011.

[15]  Trevor Darrell,et al.  Detector discovery in the wild: Joint multiple instance and representation learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Christoph H. Lampert,et al.  Curriculum learning of multiple tasks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Enver Sangineto.  Statistical and Spatial Consensus Collection for Detector Adaptation , 2014, ECCV.

[18]  Deva Ramanan,et al.  Self-Paced Learning for Long-Term Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[20]  Cordelia Schmid,et al.  Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[22]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Andrea Vedaldi,et al.  Weakly Supervised Deep Detection Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Alexei A. Efros,et al.  Undoing the Damage of Dataset Bias , 2012, ECCV.

[25]  Trevor Darrell,et al.  LSDA: Large Scale Detection through Adaptation , 2014, NIPS.

[26]  Yang Wang,et al.  Attention Networks for Weakly Supervised Object Localization , 2016, BMVC.

[27]  Ivan Laptev,et al.  Is object localization for free? - Weakly-supervised learning with convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[29]  Wojciech Zaremba,et al.  Learning to Execute , 2014, ArXiv.

[30]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[31]  Zaïd Harchaoui,et al.  On learning to localize objects with minimal supervision , 2014, ICML.

[32]  Ivan Laptev,et al.  ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization , 2016, ECCV.

[33]  Chong Wang,et al.  Large-Scale Weakly Supervised Object Localization via Latent Category Learning , 2015, IEEE Transactions on Image Processing.

[34]  Yong Jae Lee,et al.  Weakly-supervised Discovery of Visual Pattern Configurations , 2014, NIPS.

[35]  Carsten Rother,et al.  Learning discriminative localization from weakly labeled data , 2014, Pattern Recognit..

[36]  Yunchao Wei,et al.  STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation. , 2017, IEEE transactions on pattern analysis and machine intelligence.

[37]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[39]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[40]  Shiguang Shan,et al.  Self-Paced Learning with Diversity , 2014, NIPS.

[41]  Yunchao Wei,et al.  STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Cordelia Schmid,et al.  Multi-fold MIL Training for Weakly Supervised Object Localization , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[43]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[44]  Antonio Torralba,et al.  Are all training examples equally valuable? , 2013, ArXiv.

[45]  Xinlei Chen,et al.  Webly Supervised Learning of Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[46]  Ming-Hsuan Yang,et al.  Weakly Supervised Object Localization with Progressive Domain Adaptation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Tinne Tuytelaars,et al.  Weakly supervised object detection with convex clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Abhinav Gupta,et al.  Training Region-Based Object Detectors with Online Hard Example Mining , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[49]  Yunchao Wei,et al.  Computational Baby Learning , 2014, ArXiv.