Abstract
Video object detection is a fundamental yet challenging task in computer vision. One practical solution is to take advantage of temporal information from the video and apply feature aggregation to enhance the object features in each frame. Though effective, those existing methods always suffer from low inference speeds because they use a fixed number of frames for feature aggregation regardless of the input frame. Therefore, this paper aims to improve the inference speed of the current feature aggregation-based video object detectors while maintaining their performance. To achieve this goal, we propose a vanilla dynamic aggregation module that adaptively selects the frames for feature enhancement. Then, we extend the vanilla dynamic aggregation module to a more effective and reconfigurable deformable version. Finally, we introduce inplace distillation loss to improve the representations of objects aggregated with fewer frames. Extensive experimental results validate the effectiveness and efficiency of our proposed methods: On the ImageNet VID benchmark, integrated with our proposed methods, FGFA and SELSA can improve the inference speed by \(31\%\) and \(76\%\) respectively while getting comparable performance on accuracy. Codes are available at https://github.com/YimingCuiCuiCui/DFA.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For better analysis, we use the same way as FGFA [44] to categorize objects in every single frame based on their motion speeds.
- 2.
There are around \(2\%\) mAP fluctuations in performance, and we take the mean after running 5 experiments.
References
Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2019). https://doi.org/10.1109/tpami.2019.2956516
Chen, K., et al.: Optimizing video object detection via a scale-time lattice. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7814–7823 (2018)
Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10337–10346 (2020)
MMT Contributors: MMTracking: OpenMMLab video perception toolbox and benchmark (2020). https://github.com/open-mmlab/mmtracking
Cui, Y., Yan, L., Cao, Z., Liu, D.: TF-blender: temporal feature blender for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8138–8147 (2021)
Cui, Y., Yang, L., Liu, D.: Dynamic proposals for efficient object detection. arXiv preprint arXiv:2207.05252 (2022)
Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T.: Relation distillation networks for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7023–7032 (2019)
Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6569–6578 (2019)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (2015)
Gong, T., et al.: Temporal ROI align for video object recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1442–1450 (2021)
Han, L., Wang, P., Yin, Z., Wang, F., Li, H.: Exploiting better feature aggregation for video object detection. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1469–1477 (2020)
Han, L., Wang, P., Yin, Z., Wang, F., Li, H.: Class-aware feature aggregation network for video object detection. IEEE Trans. Circ. Syst. Video Technol. 32(12), 8165–8178 (2021)
Han, W., et al.: Seq-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)
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)
He, L., et al.: End-to-end video object detection with spatial-temporal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1507–1516 (2021)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Jiang, Z., Gao, P., Guo, C., Zhang, Q., Xiang, S., Pan, C.: Video object detection with locally-weighted deformable neighbors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8529–8536 (2019)
Jiang, Z., et al.: Learning where to focus for efficient video object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 18–34. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_2
Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2896–2907 (2017)
Kang, K., Ouyang, W., Li, H., Wang, X.: Object detection from video tubelets with convolutional neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https://doi.org/10.1109/cvpr.2016.95
Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 765–781. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_45
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)
Liu, C., et al.: Progressive neural architecture search. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19–34 (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
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Shvets, M., Liu, W., Berg, A.C.: Leveraging long-range temporal relationships between proposals for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9756–9764 (2019)
Sun, P., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454–14463 (2021)
Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)
Wang, S., Lu, H., Deng, Z.: Fast object detection in compressed video. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7104–7113 (2019)
Wang, S., Zhou, Y., Yan, J., Deng, Z.: Fully motion-aware network for video object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 542–557 (2018)
Wang, X., Huang, Z., Liao, B., Huang, L., Gong, Y., Huang, C.: Real-time and accurate object detection in compressed video by long short-term feature aggregation. Comput. Vis. Image Underst. 206, 103188 (2021)
Wu, B., et al.: FBNet: hardware-aware efficient convnet design via differentiable neural architecture search. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10734–10742 (2019)
Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9217–9225 (2019)
Xu, Z., Hrustic, E., Vivet, D.: Centernet heatmap propagation for real-time video object detection. In: ECCV (2020)
Yao, C.-H., Fang, C., Shen, X., Wan, Y., Yang, M.-H.: Video object detection via object-level temporal aggregation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 160–177. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_10
Yu, J., Huang, T.: Autoslim: towards one-shot architecture search for channel numbers (2019)
Yu, J., Huang, T.: Universally slimmable networks and improved training techniques (2019)
Yu, J., Yang, L., Xu, N., Yang, J., Huang, T.: Slimmable neural networks (2018)
Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 408–417 (2017)
Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2349–2358 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cui, Y. (2023). Dynamic Feature Aggregation for Efficient Video Object Detection. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13842. Springer, Cham. https://doi.org/10.1007/978-3-031-26284-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-26284-5_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26283-8
Online ISBN: 978-3-031-26284-5
eBook Packages: Computer ScienceComputer Science (R0)