Learn to Detect Objects Incrementally

Intelligent vehicles need to detect new classes of traffic objects while keeping the performance of old ones. Deep convolution neural network (DCNN) based detector has shown superior performance, however, DCNN is ill-equipped for incremental learning, i.e., a DCNN based vehicle detector trained on traffic sign dataset will catastrophic forget how to detect vehicles. In this paper, we propose a novel method to alleviate this problem, our key insight is that the original class of objects also appears in new task data, by utilizing these objects, our method effectively keeps the detection accuracy of original models while incremental learning to detect new classes of objects. Detailed experiments on PASCAL VOC dataset and TSD-max database verified the effectiveness of our method.

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

[2]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  W. Abraham,et al.  Memory retention – the synaptic stability versus plasticity dilemma , 2005, Trends in Neurosciences.

[4]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[5]  Bernt Schiele,et al.  What Makes for Effective Detection Proposals? , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[8]  Wei Liu,et al.  DSSD : Deconvolutional Single Shot Detector , 2017, ArXiv.

[9]  R. French.  Catastrophic Forgetting in Connectionist Networks , 2006 .

[10]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Pietro Perona,et al.  Pedestrian detection: A benchmark , 2009, CVPR.

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

[13]  Cordelia Schmid,et al.  Incremental Learning of Object Detectors without Catastrophic Forgetting , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[15]  Y. Nesterov.  A method for solving the convex programming problem with convergence rate O(1/k^2) , 1983 .

[16]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[17]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[18]  Anthony V. Robins,et al.  Catastrophic Forgetting, Rehearsal and Pseudorehearsal , 1995, Connect. Sci..

[19]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Ronald Kemker,et al.  Measuring Catastrophic Forgetting in Neural Networks , 2017, AAAI.

[21]  Itamar Arel,et al.  Unsupervised neuron selection for mitigating catastrophic forgetting in neural networks , 2014, 2014 IEEE 57th International Midwest Symposium on Circuits and Systems (MWSCAS).

[22]  Kaushik Roy,et al.  Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing , 2017, IEEE Access.

[23]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[24]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[25]  Chrisantha Fernando,et al.  PathNet: Evolution Channels Gradient Descent in Super Neural Networks , 2017, ArXiv.

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

[27]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[28]  Byoung-Tak Zhang,et al.  Overcoming Catastrophic Forgetting by Incremental Moment Matching , 2017, NIPS.

[29]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[30]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.