ABSTRACT
In the anchor-based object detector, the redundancy introduced by the symmetry of anchor generator will be harmful for the diversity of positive anchors and cause performance drop. A simple yet effective sampling strategy called Hard Anchor Attention (HAA) is proposed in this paper. First, the anchor generator is re-examined by studying the contribution of different samples to the overall performance. It is verified that the harder positive anchors play an important role in the training of the detector. Then the HAA is introduced to evaluate the difficulty of refining anchors, and direct the focus of the training process to such harder anchors. The experimental results demonstrate that HAA can bring performance gains to RetinaNet and further releases the subsequent branches. Particularly, without fine-tuning, on the Pascal VOC dataset, HAA outperforms the random sampling and all-in baseline.
- Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934(2020).Google Scholar
- Yuhang Cao, Kai Chen, Chen Change Loy, and Dahua Lin. 2020. Prime sample attention in object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11583–11591.Google ScholarCross Ref
- Shohei Chiba and Hisayuki Sasaoka. 2021. Effectiveness of Transfer Learning in Autonomous Driving using Model Car. In 2021 13th International Conference on Machine Learning and Computing. 595–601.Google ScholarDigital Library
- Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2010. The pascal visual object classes (voc) challenge. International journal of computer vision 88, 2 (2010), 303–338.Google ScholarDigital Library
- Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 580–587.Google ScholarDigital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.Google ScholarCross Ref
- Lichao Huang, Yi Yang, Yafeng Deng, and Yinan Yu. 2015. Densebox: Unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874(2015).Google Scholar
- Borui Jiang, Ruixuan Luo, Jiayuan Mao, Tete Xiao, and Yuning Jiang. 2018. Acquisition of localization confidence for accurate object detection. In Proceedings of the European conference on computer vision (ECCV). 784–799.Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012), 1097–1105.Google Scholar
- Hei Law and Jia Deng. 2018. Cornernet: Detecting objects as paired keypoints. In Proceedings of the European conference on computer vision (ECCV). 734–750.Google ScholarDigital Library
- Jiachen Li, Bowen Cheng, Rogerio Feris, Jinjun Xiong, Thomas S Huang, Wen-Mei Hwu, and Humphrey Shi. 2021. Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2378–2387.Google ScholarCross Ref
- Xiang Li, Wenhai Wang, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang. 2021. Generalized focal loss v2: Learning reliable localization quality estimation for dense object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11632–11641.Google ScholarCross Ref
- Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. 2017. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2117–2125.Google ScholarCross Ref
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980–2988.Google ScholarCross Ref
- Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In European conference on computer vision. Springer, 740–755.Google ScholarCross Ref
- Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, and Jiaya Jia. 2018. Path aggregation network for instance segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 8759–8768.Google ScholarCross Ref
- Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767(2018).Google Scholar
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015), 91–99.Google Scholar
- Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, and Silvio Savarese. 2019. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 658–666.Google ScholarCross Ref
- Abhinav Shrivastava, Abhinav Gupta, and Ross Girshick. 2016. Training region-based object detectors with online hard example mining. In Proceedings of the IEEE conference on computer vision and pattern recognition. 761–769.Google ScholarCross Ref
- Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http://arxiv.org/abs/1409.1556Google Scholar
- Bharat Singh and Larry S Davis. 2018. An analysis of scale invariance in object detection snip. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3578–3587.Google ScholarCross Ref
- Bharat Singh, Mahyar Najibi, and Larry S. Davis. 2018. SNIPER: Efficient Multi-Scale Training. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, and Roman Garnett (Eds.). 9333–9343. https://proceedings.neurips.cc/paper/2018/hash/166cee72e93a992007a89b39eb29628b-Abstract.htmlGoogle Scholar
- Peize Sun, Rufeng Zhang, Yi Jiang, Tao Kong, Chenfeng Xu, Wei Zhan, Masayoshi Tomizuka, Lei Li, Zehuan Yuan, Changhu Wang, 2021. Sparse r-cnn: End-to-end object detection with learnable proposals. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14454–14463.Google ScholarCross Ref
- Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2019. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF international conference on computer vision. 9627–9636.Google ScholarCross Ref
- Yuan-Kai Wang, Ching-Tang Fan, Ke-Yu Cheng, and Peter Shaohua Deng. 2011. Real-time camera anomaly detection for real-world video surveillance. In 2011 International Conference on Machine Learning and Cybernetics, Vol. 4. IEEE, 1520–1525.Google ScholarCross Ref
- Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, and Stan Z Li. 2020. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9759–9768.Google ScholarCross Ref
- Xingyi Zhou, Vladlen Koltun, and Philipp Krähenbühl. 2020. Tracking Objects as Points. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part IV(Lecture Notes in Computer Science, Vol. 12349), Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer, 474–490. https://doi.org/10.1007/978-3-030-58548-8_28Google ScholarDigital Library
Recommendations
Anchor-few: an adaptive precise indoor positioning system for low anchor densities based on IoT localization
MobiCom '22: Proceedings of the 28th Annual International Conference on Mobile Computing And NetworkingThis paper designs and implements an adaptive precise indoor positioning system, called Anchor-Few, for low anchor densities through Internet of Things (IoT) localization. Anchor Few exploits the IoT localization device, iBeacon, to provide accurate ...
UWB-based Single-anchor Low-cost Indoor Localization System
SenSys '17: Proceedings of the 15th ACM Conference on Embedded Network Sensor SystemsIn this demo, we present a low-cost indoor localization system based on the off-the-shelf ultra-wideband transceiver Decawave DW1000. To obtain an accurate position information, the system makes use of a single anchor and of multipath reflections from ...
A New Anchor-Based Localization Algorithm for Wireless Sensor Network
DCABES '11: Proceedings of the 2011 10th International Symposium on Distributed Computing and Applications to Business, Engineering and ScienceAnchor plays a very important role in range-based localization algorithm. In order to solve disadvantages of traditional localization algorithm based on anchors, this paper proposes a new anchor-based localization algorithm for wireless sensor network. ...
Comments