Abstract
To detect objects, human visual perception focuses on the key content of interest and then transmits high-level semantic information through feedback connections, selectively enhancing and suppressing neuronal activation. Inspired by the human visual system, our detector incorporates the recursive feature pyramid in the backbone to integrate the feedback information of the FPN into the backbone network so that the features of the secondary training of the backbone network can be better adapted to the detection task. Furthermore, we propose a key content-only attention mechanism to seek the balance between accuracy and efficiency, which adopts the attention configuration of the key content-only term with deformable convolution to achieve the best accuracy and efficiency trade-off. Both of these can improve our baseline AP by > 4%, and combining them further enhances the performance of our detector. On COCO test dev, our detector achieves 45.1% box AP with ResNet-50.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Beck, D.M., Kastner, S.: Top-down and bottom-up mechanisms in biasing competition in the human brain. Vis. Res. 49(10), 1154–1165 (2009)
Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154–6162 (2018)
Cao, C., et al.: Look and think twice: capturing top-down visual attention with feedback convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2956–2964 (2015)
Cao, J., Cholakkal, H., Anwer, R.M., Khan, F.S., Pang, Y., Shao, L.: D2det: towards high quality object detection and instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11485–11494 (2020)
Chen, K., et al.: Mmdetection: open MMLAB detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818 (2018)
Chiasi, G., Lin, T.Y., Le, Q.V.N.: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 7029–7038
Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764–773 (2017)
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Desimone, R.: Visual attention mediated by biased competition in extrastriate visual cortex. Philos. Trans. Roy. Soc. Lond. Ser. B: Biol. Sci. 353(1373), 1245–1255 (1998)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Jain, S., Wallace, B.C.: Attention is not explanation. arXiv preprint arXiv:1902.10186 (2019)
Jiang, C., Xu, H., Zhang, W., Liang, X., Li, Z.: Sp-nas: serial-to-parallel backbone search for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11863–11872 (2020)
Li, J., Raventos, A., Bhargava, A., Tagawa, T., Gaidon, A.: Learning to fuse things and stuff. arXiv preprint arXiv:1812.01192 (2018)
Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 510–519 (2019)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)
Liu, W., et al.: SSD: single shot multiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)
Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781–10790 (2020)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018)
Xu, H., Yao, L., Zhang, W., Liang, X., Li, Z.: Auto-fpn: automatic network architecture adaptation for object detection beyond classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6649–6658 (2019)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, Y., Zhang, T., Jin, J., Zhang, L. (2022). Object Detector with Recursive Feature Pyramid and Key Content-Only Attention. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13531. Springer, Cham. https://doi.org/10.1007/978-3-031-15934-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-15934-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15933-6
Online ISBN: 978-3-031-15934-3
eBook Packages: Computer ScienceComputer Science (R0)