自适应分离知识蒸馏的遥感目标检测

doi:10.3778/j.issn.1002-8331.2311-0170

摘要/Abstract

摘要： 近年来，深度模型在大规模应用方面取得巨大成功，但计算复杂度和存储需求等问题使它们在资源有限的设备上难以部署。知识蒸馏（KD）是一种压缩模型的方法，然而现有方法未考虑遥感数据集的特点。具体来说，在遥感数据集中由于背景复杂，图像中目标物体较小，直接应用现有的知识蒸馏方法时会出现大量噪声，影响训练性能。因此提出了自适应分离知识蒸馏（ASKD）方法。ASKD允许学生模型自动选择多尺度核心特征，减少噪声，同时通过分离全局和局部特征，有效抑制背景干扰。在LEVIR和SSDD数据集上，ASKD在单阶段和双阶段检测器上都取得了出色性能。例如，基于ResNet-18的Faster RCNN，ASKD在SSDD上实现了59.2%的mAP，比基线模型高出2.0个百分点，甚至胜过教师模型。

关键词: 知识蒸馏, 遥感, 轻量级目标检测

Abstract: In recent years, deep models have achieved great success in large-scale applications, but issues such as computational complexity and storage requirements make them difficult to deploy on resource-limited devices. Knowledge distillation (KD) is a method for compressing model, however, existing methods do not consider the characteristics of remote sensing datasets. Specifically, in remote sensing datasets due to the complex background and small target objects in the images, a large amount of noise occurs when applying the existing knowledge distillation methods directly, which affects the training performance. Therefore, the adaptive separation of knowledge distillation (ASKD) method is proposed. ASKD allows the student model to automatically select multi-scale core features to reduce noise, and at the same time effectively suppresses background interference by separating global and local features. ASKD achieves excellent performance on both single-stage and two-stage detectors on both LEVIR and SSDD datasets. For example, based on Faster RCNN of ResNet-18, ASKD achieves 59.2% mAP on SSDD, which is 2.0 percentage points higher than the baseline model and even better than the teacher model.

Key words: knowledge distillation, remote sensing, lightweight object detection

杨晓雨, 顾进广. 自适应分离知识蒸馏的遥感目标检测[J]. 计算机工程与应用, 2025, 61(6): 295-303.

YANG Xiaoyu, GU Jinguang. Adaptive Separation of Knowledge Distillation for Remote Sensing Object Detection[J]. Computer Engineering and Applications, 2025, 61(6): 295-303.

参考文献

[1] PENG S. Application of medical image detection technology based on deep learning in pneumoconiosis diagnosis[J]. Data Intelligence, 2023, 5(4): 1033-1047.
[2] 张婷, 张兴忠, 王慧民, 等. 基于图神经网络的变电站场景三维目标检测[J]. 计算机工程与应用, 2023, 59(9): 329-336.
ZHANG T, ZHANG X Z, WANG H M, et al. 3D object detection in substation scene based on graph neural nerwork[J]. Computer Engineering and Applications, 2023, 59(9): 329-336.
[3] ZHANG T, YE S, ZHANG K, et al. A systematic DNN weight pruning framework using alternating direction method of multipliers[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 184-199.
[4] LI R, WANG Y, LIANG F, et al. Fully quantized network for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2019: 2810-2819.
[5] HAN K, WANG Y, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
[6] 黄磊, 杨媛, 杨成煜, 等. FS-YOLOv5: 轻量化红外目标检测方法[J]. 计算机工程与应用, 2023, 59(9): 215-224.
HUANG L, YANG Y, YANG C Y, et al. FS-YOLOv5: ligntweight infrared rode target detection method[J]. Computer Engineering and Applications, 2023, 59(9): 215-224.
[7] ZHU J, TANG S, CHEN D, et al. Complementary relation contrastive distillation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 9260-9269.
[8] ROMERO A, BALLAS N, KAHOU S E, et al. FitNets: hints for thin deep nets[J]. arXiv:1412.6550, 2014.
[9] HINTON G, VINYALS O, DEAN J. Distilling the knowledge in a neural network[J]. arXiv:1503.02531, 2015.
[10] HEO B, LEE M, YUN S, et al. Knowledge transfer via distillation of activation boundaries formed by hidden neurons[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 3779-3787.
[11] WANG T, YUAN L, ZHANG X, et al. Distilling object detectors with fine-grained feature imitation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 4933-4942.
[12] GUO J, HAN K, WANG Y, et al. Distilling object detectors via decoupled features[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 2154-2164.
[13] ZHANG L, MA K. Improve object detection with feature-based knowledge distillation: towards accurate and efficient detectors[C]//Proceedings of the International Conference on Learning Representations, 2020.
[14] DU Z X, ZHANG R, CHANG M, et al. Distilling object detectors with feature richness[C]//Advances in Neural Information Processing Systems, 2021: 5213-5224.
[15] YANG Z, LI Z, JIANG X, et al. Focal and global knowledge distillation for detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 4643-4652.
[16] ZOU Z, SHI Z. Random access memories: a new paradigm for target detection in high resolution aerial remote sensing images[J]. IEEE Transactions on Image Processing, 2017, 27(3): 1100-1111.
[17] LI J, QU C, SHAO J. Ship detection in SAR images based on an improved faster R-CNN[C]//Proceedings of the 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA), 2017: 1-6.
[18] ZHANG S, WEN L, BIAN X, et al. Single-shot refinement neural network for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4203-4212.
[19] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 2016: 21-37.
[20] HU H, GU J, ZHANG Z, et al. Relation networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 3588-3597.
[21] HUANG J, RATHOD V, SUN C, et al. Speed/accuracy trade-offs for modern convolutional object detectors[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7310-7311.
[22] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
[23] TIAN Z, SHEN C, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 9627-9636.
[24] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015.
[25] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[J]. arXiv:1704.04861, 2017.
[26] SUN X, LIU Y, YAN Z, et al. SRAF-Net: shape robust anchor-free network for garbage dumps in remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 59(7): 6154-6168.
[27] XU T, SUN X, DIAO W, et al. ASSD: feature aligned single-shot detection for multiscale objects in aerial imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 1-17.
[28] ZAGORUYKO S, KOMODAKIS N. Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer[J]. arXiv:1612.03928, 2016.
[29] FARHADI M, YANG Y. TKD: temporal knowledge distillation for active perception[C]//Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020: 942-951.
[30] LIU Y, CHEN K, LIU C, et al. Structured knowledge distillation for semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 2604-2613.
[31] GE S, ZHAO S, LI C, et al. Low-resolution face recognition in the wild via selective knowledge distillation[J]. IEEE Transactions on Image Processing, 2018, 28(4): 2051-2062.
[32] XU C, ZHOU W, GE T, et al. BERT-of-theseus: compressing bert by progressive module replacing[J]. arXiv:2002.02925, 2020.
[33] CHEN G, CHOI W, YU X, et al. Learning efficient object detection models with knowledge distillation[C]//Advances in Neural Information Processing Systems, 2017.
[34] LI Q, JIN S, YAN J. Mimicking very efficient network for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6356-6364.
[35] DAI X, JIANG Z, WU Z, et al. General instance distillation for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 7842-7851.
[36] YANG Y, SUN X, DIAO W, et al. Adaptive knowledge distillation for lightweight remote sensing object detectors optimizing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-15.
[37] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.
[38] CAO Y, XU J, LIN S, et al. GCNet: non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019.
[39] CHEN K, WANG J, PANG J, et al. MMDetection: open mmlab detection toolbox and benchmark[J]. arXiv:1906. 07155, 2019.
[40] LI X, WANG W, WU L, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[C]//Advances in Neural Information Processing Systems, 2020: 21002-21012.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	69

	来源	本网站

	次数	69
	比例	100%

摘要

最新录用	在线预览	正式出版

0	0	53

	来源	本网站

	次数	53
	比例	100%