2000 character limit reached
Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking (2402.16570v2)
Published 26 Feb 2024 in cs.CV and cs.LG
Abstract: Manually-designed network architectures for thermal infrared pedestrian tracking (TIR-PT) require substantial effort from human experts. AlexNet and ResNet are widely used as backbone networks in TIR-PT applications. However, these architectures were originally designed for image classification and object detection tasks, which are less complex than the challenges presented by TIR-PT. This paper makes an early attempt to search an optimal network architecture for TIR-PT automatically, employing single-bottom and dual-bottom cells as basic search units and incorporating eight operation candidates within the search space. To expedite the search process, a random channel selection strategy is employed prior to assessing operation candidates. Classification, batch hard triplet, and center loss are jointly used to retrain the searched architecture. The outcome is a high-performance network architecture that is both parameter- and computation-efficient. Extensive experiments proved the effectiveness of the automated method.
- X. Zhong, T. Lu, W. Huang, M. Ye, X. Jia, and C.-W. Lin, “Grayscale enhancement colorization network for visible-infrared person re-identification,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 3, pp. 1418–1430, 2022.
- A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.
- K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556v6, 2015.
- K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.
- Q. Liu, D. Yuan, N. Fan, P. Gao, X. Li, and Z. He, “Learning dual-level deep representation for thermal infrared tracking,” IEEE Transactions on Multimedia, vol. 25, pp. 1269–1281, 2022.
- P. Gao, Y. Ma, K. Song, C. Li, F. Wang, and L. Xiao, “Large margin structured convolution operator for thermal infrared object tracking,” in IEEE International Conference on Pattern Recognition, 2018, pp. 2380–2385.
- D. Yuan, X. Shu, Q. Liu, and Z. He, “Aligned spatial-temporal memory network for thermal infrared target tracking,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 70, no. 3, pp. 1224–1228, 2022.
- H. Huang, L. Shen, C. He, W. Dong, and W. Liu, “Differentiable neural architecture search for extremely lightweight image super-resolution,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 6, pp. 2672–2682, 2023.
- L. Cai, Y. Fu, W. Huo, Y. Xiang, T. Zhu, Y. Zhang, H. Zeng, and D. Zeng, “Multiscale attentive image de-raining networks via neural architecture search,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 2, pp. 618–633, 2023.
- B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, “Learning transferable architectures for scalable image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8697–8710.
- E. Real, A. Aggarwal, Y. Huang, and Q. V. Le, “Regularized evolution for image classifier architecture search,” in AAAI Conference on Artificial Intelligence, vol. 33, no. 01, 2019, pp. 4780–4789.
- G. Bhat, M. Danelljan, L. V. Gool, and R. Timofte, “Learning discriminative model prediction for tracking,” in International Conference on Computer Vision (ICCV). IEEE, 2019, pp. 6182–6191.
- P. Gao, X. Liu, H.-C. Sang, Y. Wang, and F. Wang, “Efficient and lightweight visual tracking with differentiable neural architecture search,” Electronics, vol. 12, no. 17, p. 3623, 2023.
- Y. Xu, L. Xie, X. Zhang, X. Chen, G.-J. Qi, Q. Tian, and H. Xiong, “Pc-darts: Partial channel connections for memory-efficient architecture search,” in International Conference on Learning Representations, 2019.
- Q. Liu, X. Li, D. Yuan, C. Yang, X. Chang, and Z. He, “Lsotb-tir: A large-scale high-diversity thermal infrared single object tracking benchmark,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
- Q. Liu, Z. He, X. Li, and Y. Zheng, “Ptb-tir: A thermal infrared pedestrian tracking benchmark,” IEEE Transactions on Multimedia, vol. 22, no. 3, pp. 666–675, 2019.
- D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
- I. Loshchilov and F. Hutter, “Sgdr: Stochastic gradient descent with warm restarts,” arXiv preprint arXiv:1608.03983, 2016.
- L. Zhang, A. Gonzalez-Garcia, J. Van De Weijer, M. Danelljan, and F. S. Khan, “Synthetic data generation for end-to-end thermal infrared tracking,” IEEE Transactions on Image Processing, vol. 28, no. 4, pp. 1837–1850, 2018.
- X. Li, Q. Liu, N. Fan, Z. He, and H. Wang, “Hierarchical spatial-aware siamese network for thermal infrared object tracking,” Knowledge-Based Systems, vol. 166, pp. 71–81, 2019.
- Q. Liu, X. Lu, Z. He, C. Zhang, and W.-S. Chen, “Deep convolutional neural networks for thermal infrared object tracking,” Knowledge-Based Systems, vol. 134, pp. 189–198, 2017.
- H. Nam and B. Han, “Learning multi-domain convolutional neural networks for visual tracking,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016, pp. 4293–4302.
- Q. Liu, X. Li, Z. He, N. Fan, D. Yuan, and H. Wang, “Learning deep multi-level similarity for thermal infrared object tracking,” IEEE Transactions on Multimedia, vol. 23, pp. 2114–2126, 2020.
- X. Li, C. Ma, B. Wu, Z. He, and M.-H. Yang, “Target-aware deep tracking,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 1369–1378.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.