Abstract
Object detection, an important task in computer vision, has achieved a conspicuous improvement. Among the methods for object detection, the one-stage detector is a simple, end-to-end, anchor-free, and straightforward deep learning pipeline. Many one-stage detectors locate the bounding box using regression, and the regression loss is the maximum among all errors. Hence, locating the bounding box accurately is one of the keys for improving the average precision (AP) for a detector. In this paper, we suggest a simple and precise locator named the bounding convolutional network (BoundConvNet) to draw “bounding features” from heatmaps to refine the object locations and apply a category-aware collaborative intersection over union (Co-IoU) loss function to optimize the bounding box regression for dealing with a problem of different class center point overlap. BoundConvNet is a head network for bounding box regression, which contains several depthwise separable dilated convolutional layers to decouple the classification task from the regression task. Extensive experiments demonstrate that BoundConvNet improves the AP of the one-stage detector CenterNet and helps the CenterNet mark the bounding box of objects more accurately. For small object detection, the AP of CenterNet is improved by 13.8% relative on MS COCO dataset with ResNet-18 as backbone.
Similar content being viewed by others
Data availability
Some or all data, models or code generated or used during the study are available from the first author and the corresponding author on reasonable request.
References
Szegedy C, Toshev A, Erhan D (2013) Deep neural networks for object detection. l2013 - research. Google
Li Y, Qi H, Dai J, Ji X, Wei Y (2017) Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2359–2367
Kompella A, Kulkarni RV (2021) A semi-supervised recurrent neural network for video salient object detection. Neural Comput Appl 33(6):2065–2083
Chawla A, Yin H, Molchanov P, Alvarez J (2021) Data-free knowledge distillation for object detection. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 3289–3298
Girshick R, Donahue J, Darrell T, Malik J (2014) 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
He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916
Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91–99
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision, Springer, pp 21–37
Zhou X, Wang D, Krähenbühl P (2019) Objects as points. arXiv preprint arXiv:1904.07850
Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 9627–9636
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Yu F, Wang D, Shelhamer E, Darrell T (2018) Deep layer aggregation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2403–2412
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vision 104(2):154–171
Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE conference on computer vision and pattern recognition, pp 1–8
Wang X, Chen K, Huang Z, Yao C, Liu W (2017) Point linking network for object detection. arXiv preprint arXiv:1706.03646
Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734–750
Zhou X, Zhuo J, Krahenbuhl P (2019) Bottom-up object detection by grouping extreme and center points. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 850–859
Qiu H, Ma Y, Li Z, Liu S, Sun J (2020) Borderdet: Border feature for dense object detection. In: European conference on computer vision, Springer, pp 549–564
Yang Z, Liu S, Hu H, Wang L, Lin S (2019) Reppoints: point set representation for object detection. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 9657–9666
Vu T, Jang H, Pham TX, Yoo CD (2019) Cascade rpn: Delving into high-quality region proposal network with adaptive convolution. arXiv preprint arXiv:1909.06720
Zhu X, Hu H, Lin S, Dai J (2019) Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 9308–9316
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248–255
Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117–2125
Lin T-Y, Goyal P, Girshick R, He K, Dollár P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980–2988
Wu Y, Chen Y, Yuan L, Liu Z, Wang L, Li H, Fu Y (2020) Rethinking classification and localization for object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10186–10195
Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision, Springer, pp 483–499
Lan S, Ren Z, Wu Y, Davis LS, Hua G (2020) Saccadenet: a fast and accurate object detector. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10397–10406
Park H-J, Choi Y-J, Lee Y-W, Kim B-G (2022) ssfpn: Scale sequence (s\(^{\hat{}}{2}\)) feature based-feature pyramid network for object detection. arXiv e-prints, 2208
Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258
He Y, Zhu C, Wang J, Savvides M, Zhang X (2019) Bounding box regression with uncertainty for accurate object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2888–2897
Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision, Springer, pp 740–755
Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vision 88(2):303–338
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141
Zhang W, Fu C, Xie H, Zhu M, Tie M, Chen J (2021) Global context aware rcnn for object detection. Neural Comput Appl 33(18):11627–11639
Nguyen N-D, Do T, Ngo TD, Le D-D (2020) An evaluation of deep learning methods for small object detection. J Electr Comput Eng 2020:1–18
Vandenhende S, Georgoulis S, Van Gansbeke W, Proesmans M, Dai D, Van Gool L (2021) Multi-task learning for dense prediction tasks: A survey. IEEE Trans Pattern Anal Mach Intell 44(7):3614–3633
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Wang X, Zhu D, Yan Y (2022) Towards efficient detection for small objects via attention-guided detection network and data augmentation. Sensors 22(19):7663
Farhadi A, Redmon J (2018) Yolov3: an incremental improvement. In: Computer vision and pattern recognition, vol. 1804. Springer Berlin/Heidelberg, Germany, p 1–6
Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934
Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4203–4212
Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430
Xu S, Wang X, Lv W, Chang Q, Cui C, Deng K, Wang G, Dang Q, Wei S, Du Y, et al (2022) Pp-yoloe: An evolved version of yolo. arXiv preprint arXiv:2203.16250
Glenn J (2022) YOLOv5 release v6.1. https://github.com/ ultralytics/yolov5/releases/tag/v6.1/
Wang C-Y, Yeh I-H, Liao H-YM (2021) You only learn one representation: Unified network for multiple tasks. arXiv preprint arXiv:2105.04206
Wang C-Y, Bochkovskiy A, Liao H-YM (2022) Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696
Chicco D, Jurman G (2020) The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation. BMC Genom 21:1–13
Acknowledgements
This work was supported by the Science and Technology Development Fund (FDCT) of Macau under Grant No. 0071/2022/A.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, S., Wang, W., Li, H. et al. Bounding convolutional network for refining object locations. Neural Comput & Applic 35, 19297–19313 (2023). https://doi.org/10.1007/s00521-023-08782-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08782-9