Adaptive separation fusion: a novel downsampling approach in CNNS

• Autorzy: Ji Xia , Chang Jinglong , Ji Yapeng

Identyfikatory

DOI

10.2478/jaiscr-2025-0010

• Języki publikacji: EN

Abstrakty

EN

Almost all computer vision tasks rely on convolutional neural networks and transformers, both of which require extensive computations. With the increasingly large size of images, it becomes challenging to input these images directly. Therefore, in typical cases, we downsample the images to a reasonable size before proceeding with subsequent tasks. However, the downsampling process inevitably discards some fine-grained information, leading to network performance degradation. Existing methods, such as strided convolution and various pooling techniques, struggle to address this issue effectively. To overcome this limitation, we propose a generalized downsampling module, Adaptive Separation Fusion Downsampling (ASFD). ASFD adaptively captures intra- and inter-region attentional relationships and preserves feature representations lost during downsampling through fusion. We validate ASFD on representative computer vision tasks, including object detection and image classification. Specifically, we incorporated ASFD into the YOLOv7 object detection model and several classification models. Experiments demonstrate that the modified YOLOv7 architecture surpasses state-of-the-art models in object detection, particularly excelling in small object detection. Additionally, our method outperforms commonly used downsampling techniques in classification tasks. Furthermore, ASFD functions as a plug-and-play module compatible with various network architectures.

Słowa kluczowe

EN

adaptive; object detection; image classification; deep learing; downsampling

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2025
• Tom: Vol. 15, No. 2
• Strony: 197--210
• Opis fizyczny: Bibliogr. 30 poz., rys.

Twórcy

autor

Ji Xia

• School of Computer Science and Technology, Anhui University
• Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging

• https://orcid.org/0000-0002-2820-0405

autor

Chang Jinglong

• School of Computer Science and Technology, Anhui University

• https://orcid.org/0009-0005-5363-4271

autor

Ji Yapeng

• School of Computer Science and Technology, Anhui University

• https://orcid.org/0009-0001-7287-1302

Bibliografia

• [1] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2014.
• [2] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.
• [3] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580–587, 2014.
• [4] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp. 234–241, Springer, 2015.
• [5] W. Zhang, Z. Hong, L. Xiong, Z. Zeng, Z. Cai, and K. Tan, “Sinextnet: A new small object detection model for aerial images based on pp-yoloe,” Journal of Artificial Intelligence and Soft Computing Research, vol. 14, no. 3, pp. 251–265.
• [6] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-end object detection with transformers,” in European conference on computer vision, pp. 213–229, Springer, 2020.
• [7] Y.-L. Boureau, F. Bach, Y. LeCun, and J. Ponce, “Learning mid-level features for recognition,” in 2010 IEEE computer society conference on computer vision and pattern recognition, pp. 2559–2566, IEEE, 2010.
• [8] Y.-L. Boureau, J. Ponce, and Y. LeCun, “A theoretical analysis of feature pooling in visual recognition,” in Proceedings of the 27th international conference on machine learning (ICML-10), pp. 111–118, 2010.
• [9] A. Stergiou, R. Poppe, and G. Kalliatakis, “Refining activation downsampling with softpool,” in Proceedings of the IEEE/CVF international conference on computer vision, pp. 10357–10366, 2021.
• [10] M. D. Zeiler and R. Fergus, “Stochastic pooling for regularization of deep convolutional neural networks,” 2013.
• [11] D. Yu, H. Wang, P. Chen, and Z. Wei, “Mixed pooling for convolutional neural networks,” in Rough Sets and Knowledge Technology: 9th International Conference, RSKT 2014, Shanghai, China, October 24-26, 2014, Proceedings 9, pp. 364–375, Springer, 2014.
• [12] C. Gulcehre, K. Cho, R. Pascanu, and Y. Bengio, “Learned-norm pooling for deep feedforward and recurrent neural networks,” in Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2014, Nancy, France, September 15-19, 2014. Proceedings, Part I 14, pp. 530–546, Springer, 2014.
• [13] S. Zhai, H. Wu, A. Kumar, Y. Cheng, Y. Lu, Z. Zhang, and R. Feris, “S3pool: Pooling with stochastic spatial sampling,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4970–4978, 2017.
• [14] Z. Gao, L. Wang, and G. Wu, “Lip: Local importance-based pooling,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3355–3364, 2019.
• [15] J. Zhao and C. G. M. Snoek, “Liftpool: Bidirectional convnet pooling,” 2021.
• [16] Q. Zhu, J. Huang, N. Zheng, H. Gao, C. Li, Y. Xu, F. Zhao, et al., “Fouridown: factoring down-sampling into shuffling and superposing,” Advances in Neural Information Processing Systems, vol. 36, 2024.
• [17] R. Sunkara and T. Luo, “No more strided convolutions or pooling: A new cnn building block for low-resolution images and small objects,” in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 443–459, Springer, 2022.
• [18] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: analysis, applications, and prospects,” IEEE transactions on neural networks and learning systems, vol. 33, no. 12, pp. 6999–7019, 2021.
• [19] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
• [20] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, “An image is worth 16x16 words: Transformers for image recognition at scale,” 2020.
• [21] S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “Cbam: Convolutional block attention module,” in Proceedings of the European conference on computer vision (ECCV), pp. 3–19, 2018.
• [22] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 7464–7475, 2023.
• [23] H. Su, S. Wei, S. Liu, J. Liang, C. Wang, J. Shi, and X. Zhang, “Hq-isnet: High-quality instance segmentation for remote sensing imagery,” Remote Sensing, vol. 12, no. 6, p. 989, 2020.
• [24] G. Jocher, “YOLOv5 by Ultralytics,” May 2020.
• [25] C. Li, L. Li, H. Jiang, K. Weng, Y. Geng, L. Li, Z. Ke, Q. Li, M. Cheng, W. Nie, Y. Li, B. Zhang, Y. Liang, L. Zhou, X. Xu, X. Chu, X. Wei, and X. Wei, “Yolov6: A single-stage object detection framework for industrial applications,” 2022.
• [26] Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, “Yolox: Exceeding yolo series in 2021,” 2021.
• [27] G. Jocher, A. Chaurasia, and J. Qiu, “Ultralytics YOLO,” Jan. 2023.
• [28] Y. Le and X. Yang, “Tiny imagenet visual recognition challenge,” CS 231N, vol. 7, no. 7, p. 3, 2015.
• [29] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” 2017.
• [30] J. Chen, S.-h. Kao, H. He, W. Zhuo, S. Wen, C.-H. Lee, and S.-H. G. Chan, “Run, don’t walk: Chasing higher flops for faster neural networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12021–12031, 2023.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).