Enhanced SSD with interactive multi-scale attention features for object detection

Multimedia Tools and Applications - Tập 80 - Trang 11539-11556 - 2021
Shuren Zhou1, Jia Qiu1
1School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, China

Tóm tắt

Single Shot MultiBox Detector (SSD) method using multi-scale feature maps for object detection, showing outstanding performance in object detection task. However, as a one-stage detection method, it’s difficult for SSD methods to quickly notice significant areas of objects in the image. In the SSD network structure, feature maps of different scales are used to independently predict object, and there is a lack of interaction between low-level feature maps and high-level feature maps. In this paper we propose an enhanced SSD method using interactive multi-scale attention features (MA-SSD). Our method uses the attention mechanism to generate attention features of multiple scales and adds it to the original detection branch of the SSD method, which effectively enhances the feature representation ability and improves the detection accuracy. At the same time, the feature of different detection scales interacts with each other, and all the detection branches in our method have a parallel structure, which ensures the detection efficiency. Our proposed method achieves competitive performance on the public dataset PascalVOC.

Tài liệu tham khảo

Anderson P, He XD, Buehler C (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 6077–6086. https://doi.org/10.1109/CVPR.2018.00636 Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 Buzcu I, Alatan AA (2016) Fisher-selective search for object detection. In: IEEE International Conference on Image Processing, pp. 3633–3637, ICIP. https://doi.org/10.1109/ICIP.2016.7533037 Cai Z, Vasconcelos N (2018) Cascade R-CNN: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154–6162, CVPR. https://doi.org/10.1109/CVPR.2018.00644 Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol 1, pp 886–893. https://doi.org/10.1109/CVPR.2005.177 Everingham M, Eslami SMA (2007) The Pascal visual object classes challenge 2007 (VOC2007) development kit. Int J Comput Vis 111(1):98–136. https://doi.org/10.1007/s11263-014-0733-5 Fu C, Liu W, Ranga A (2017) DSSD: Deconvolutional Single Shot Detector arXiv:1701.06659 Girshick R (2015) Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448, ICCV. https://doi.org/10.1109/ICCV.2015.169 Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587, CVPR. https://doi.org/10.1109/CVPR.2014.81 Gui Y, Zeng G (2020) Joint learning of visual and spatial features for edit propagation from a single image. Vis Comput 36:469–482. https://doi.org/10.1007/s00371-019-01633-6 He K, Zhang X, Ren S (2014) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. Eur Conf Comput Vis, pp. 346–361, ECCV. https://doi.org/10.1007/978-3-319-10578-9_23 He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. CVPR. https://doi.org/10.1109/CVPR.2016.90 Hu H, Gu JY, Zhang Z, Dai J, Wei YC (2018) Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588–3597, CVPR. https://doi.org/10.1109/CVPR.2018.00378 Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely Connected Convolutional Networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261–2269, CVPR. https://doi.org/10.1109/CVPR.2017.243 Jia D, Wei D, Richard S, Lijia L, Kai L, Feifei L (2009) ImageNet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2009:248–255, CVPR. https://doi.org/10.1109/CVPR.2009.5206848 Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444. https://doi.org/10.1038/nature14539 Li W, Xu H, Li H, Yang YJ, Sharma PK, Wang J, Singh S (2020) Complexity and algorithms for superposed data uploading problem in networks with smart devices. IEEE Internet Things J pp. 1–1. https://doi.org/10.1109/jiot.2019.2949352 Lin TY, Dollar P, Girshick R (2017) Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 936–944, CVPR. https://doi.org/10.1109/CVPR.2017.106 Lin T, Goyal P, Girshick R, He K, Dollar P (2018) Focal loss for dense object detection. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 42, no 2, pp 318–327. https://doi.org/10.1109/TPAMI.2018.2858826 Liu W, Anguelov D, Erhan D, Christian S, Scott R, Cheng-Yang F, Alexander C (2016) SSD: single shot MultiBox detector. In: European conference on computer vision. Pp. 21-37, ECCV. https://doi.org/10.1007/978-3-319-46448-0_2 Mnih V, Heess N, Graves A (2014) Recurrent models of visual attention. In: Advances in neural information processing systems, pp. 2204–2212, NIPS. Qin J, Li H, Xiang X, Tan Y, Pan W, Xiong NN (2019) An encrypted image retrieval method based on Harris corner optimization and LSH in cloud computing. IEEE Access 7(1):24626–24633. https://doi.org/10.1109/ACCESS.2019.2894673 Redmon J, Farhadi A (2017) YOLO9000: Better, Faster, Stronger. In: The IEEE Conference on Computer Vision and Pattern Recognition. pp. 6517–6525, CVPR. https://doi.org/10.1109/CVPR.2017.690 Redmon J, Farhadi A (2018) YOLOv3: An Incremental Improvement Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788, CVPR. https://doi.org/10.1109/CVPR.2016.91 Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 39, no 6, pp 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031 Sempau J, Wilderman SJ, Bielajew AF (2000) DPM, a fast, accurate Monte Carlo code optimized for photon and electron radiotherapy treatment planning dose calculations. Phys Med Biol 45(8):2263–2291. https://doi.org/10.1088/0031-9155/45/8/315 Simonyan, K., Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:14091556 Stollenga M, Masci J, Gomez F, Schmidhuber J (2014) Deep networks with internal selective attention through feedback connections. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, vol 2, pp 3545–3553, NIPS Tang Q, Xie MZ, Yang K, Yuansheng L, Dongdai Z, Yun S (2019) A decision function based smart charging and discharging strategy for electric vehicle in smart grid. Mob Netw Appl 24:1722–1731. https://doi.org/10.1007/s11036-018-1049-4 Wang F, Jiang M, Qian C, et al. (2017) Residual attention network for image classification. IEEE Conf Comput Vis Pattern Recognit, pp. 6450–6458, CVPR. https://doi.org/10.1109/CVPR.2017.683 Wang J, Gao Y, Yin X, Li F, Kim H (2018) An Enhanced PEGASIS Algorithm with Mobile Sink Support for Wireless Sensor Networks. Wirel Commun Mob Comput (9 pages). https://doi.org/10.1155/2018/9472075 Xiao T, Xu Y, Yang K, Zhang J, Peng Y, Zhang Z (2015) The application of two-level attention models in deep convolutional neural network for fine-grained image classification. IEEE Conf Comput Vis Pattern Recognit, pp.842–850, CVPR. https://doi.org/10.1109/CVPR.2015.7298685 Zeng D, Dai Y, Li F, Sherratt RS, Wang J (2018) Adversarial learning for distant supervised relation extraction. Comput Mater Contin 55(1):121–136. https://doi.org/10.3970/cmc.2018.055.121 Zhan D, Yin T, Yang G, Xia M, Li L, Sun X (2017) Detecting image seam carving with low scaling ratio using multi-scale spatial and spectral entropies. J Vis Commun Image Represent 48:281–291. https://doi.org/10.1016/j.jvcir.2017.07.006 Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4203–4212, CVPR. https://doi.org/10.1109/CVPR.2018.00442 Zhang Z, Qiao S, Xie C, Shen W, Wang B, Yuille AL (2018) Single-shot object detection with enriched semantics. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5813–5821, CVPR. https://doi.org/10.1109/CVPR.2018.00609 Zhang J, Jin X, Sun J, Wang J, Arun KS (2020) Spatial and semantic convolutional features for robust visual object tracking. Multimed Tools Appl 79:15095–15115. https://doi.org/10.1007/s11042-018-6562-8 Zhaowei C, Quanfu F, Rogerio SF, Nuno V (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: European Conference on Computer Vision, pp. 354–370, ECCV. https://doi.org/10.1007/978-3-319-46493-0_22