Contextual Relabelling of Detected Objects

Contextual information, such as the co-occurrence of objects and the spatial and relative size among objects provides deep and complex information about scenes. It also can play an important role in improving object detection. In this work, we present two contextual models (rescoring and re-labeling models) that leverage contextual information (16 contextual relationships are applied in this paper) to enhance the state-of-the-art RCNN-based object detection (Faster RCNN). We experimentally demonstrate that our models lead to enhancement in detection performance using the most common dataset used in this field (MSCOCO).

[1]  Yichen Wei,et al.  Relation Networks for Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Matti Pietikäinen,et al.  Deep Learning for Generic Object Detection: A Survey , 2018, International Journal of Computer Vision.

[3]  Sinan Kalkan,et al.  Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation , 2016, IEEE Transactions on Cognitive and Developmental Systems.

[4]  Pushmeet Kohli,et al.  Graph Cut Based Inference with Co-occurrence Statistics , 2010, ECCV.

[5]  Shiguang Shan,et al.  Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Antonio Torralba,et al.  Context models and out-of-context objects , 2012, Pattern Recognit. Lett..

[7]  Bo Dai,et al.  Detecting Visual Relationships with Deep Relational Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Michael S. Bernstein,et al.  Visual Relationship Detection with Language Priors , 2016, ECCV.

[9]  Sinan Kalkan,et al.  COSMO: Contextualized Scene Modeling with Boltzmann Machines , 2018, Robotics Auton. Syst..

[10]  Bastian Leibe,et al.  Visual Object Recognition , 2011, Visual Object Recognition.

[11]  Serge J. Belongie,et al.  Object categorization using co-occurrence, location and appearance , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[13]  Horace Ho-Shing Ip.  Contextual Kernel and Spectral Methods for Learning the Semantics of Images , 2011, IEEE Transactions on Image Processing.

[14]  S. Ullman,et al.  Spatial Context in Recognition , 1996, Perception.

[15]  Antonio Torralba,et al.  A Tree-Based Context Model for Object Recognition , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[17]  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.

[18]  I. Biederman,et al.  Scene perception: Detecting and judging objects undergoing relational violations , 1982, Cognitive Psychology.

[19]  Kiyoharu Aizawa,et al.  Object detection refinement using Markov random field based pruning and learning based rescoring , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[20]  Sanja Fidler,et al.  The Role of Context for Object Detection and Semantic Segmentation in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Liu Jun,et al.  A review of object detection based on convolutional neural network , 2017, 2017 36th Chinese Control Conference (CCC).

[22]  Serge J. Belongie,et al.  Context based object categorization: A critical survey , 2010, Comput. Vis. Image Underst..