Fuxing Leng
ABSTRACT
This paper presents the 1st place solution to the Grand Challenge of ACM MM2021 Robust Logo Detection. We build our end-to-end solution on top of Cascade RCNN (using Res2Net101 as backbone). Through careful observation during training, we find that the model performance is limited by imbalanced gradients from different classes of the long-tailed dataset. We adopt a gradient balancing approach to tackle this problem. Our approach reweighs the gradients of each class to guide the training process towards a balance between all classes. Moreover, we design a series of data augmentation policies and propose a progressive data augmentation strategy to train our model to deal with adversarial samples. We demonstrate the accuracy and robustness of our method by achieving 70.2448 mAP on leaderboard A, and 63.8793 mAP on leaderboard B, which contains adversarial images.
- Zhaowei Cai and Nuno Vasconcelos. 2017. Cascade R-CNN: Delving into High Quality Object Detection. CoRR abs/1712.00726 (2017). arXiv:1712.00726 http://arxiv.org/abs/1712.00726Google Scholar
- Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun,Wansen Feng, Ziwei Liu, Jiarui Xu, et al. 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019).Google Scholar
- 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
- Shanghua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, and Philip HS Torr. 2019. Res2net: A new multi-scale backbone architecture. IEEE transactions on pattern analysis and machine intelligence (2019).Google Scholar
- Ross Girshick. 2015. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision. 1440--1448. Google ScholarDigital Library
- Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. 2015. Regionbased convolutional networks for accurate object detection and segmentation. IEEE transactions on pattern analysis and machine intelligence 38, 1 (2015), 142--158. Google ScholarDigital Library
- Agrim Gupta, Piotr Dollar, and Ross Girshick. 2019. LVIS: A dataset for large vocabulary instance segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5356--5364.Google ScholarCross Ref
- 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
- Xuan Jin, Wei Su, Rong Zhang, Yuan He, and Hui Xue. 2020. The Open Brands Dataset: Unified brand detection and recognition at scale. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4387--4391.Google ScholarCross Ref
- Alexander B. Jung, Kentaro Wada, Jon Crall, Satoshi Tanaka, Jake Graving, Christoph Reinders, Sarthak Yadav, Joy Banerjee, Gábor Vecsei, Adam Kraft, Zheng Rui, Jirka Borovec, Christian Vallentin, Semen Zhydenko, Kilian Pfeiffer, Ben Cook, Ismael Fernández, François-Michel De Rainville, Chi-Hung Weng, Abner Ayala-Acevedo, Raphael Meudec, Matias Laporte, et al. 2020. imgaug. https://github.com/aleju/imgaug. Online; accessed 01-Feb-2020.Google Scholar
- Yu Li, TaoWang, Bingyi Kang, Sheng Tang, ChunfengWang, Jintao Li, and Jiashi Feng. 2020. Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10991--11000.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, 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
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In European conference on computer vision. Springer, 21--37.Google ScholarCross Ref
- Joseph Redmon and Ali Farhadi. 2017. YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7263--7271.Google ScholarCross Ref
- 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 ScholarDigital Library
- Jingru Tan, Xin Lu, Gang Zhang, Changqing Yin, and Quanquan Li. 2021. Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1685--1694.Google ScholarCross Ref
- Jingru Tan, Changbao Wang, Buyu Li, Quanquan Li, Wanli Ouyang, Changqing Yin, and Junjie Yan. 2020. Equalization loss for long-tailed object recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 11662--11671.Google ScholarCross Ref
- Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He. 2017. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1492--1500.Google ScholarCross Ref
- Haoyang Zhang, Ying Wang, Feras Dayoub, and Niko Sünderhauf. 2020. Swa object detection. arXiv preprint arXiv:2012.12645 (2020).Google Scholar
- Xizhou Zhu, Han Hu, Stephen Lin, and Jifeng Dai. 2019. Deformable convnets v2: More deformable, better results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9308--9316.Google ScholarCross Ref
- Barret Zoph, Ekin D Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, and Quoc V Le. 2020. Learning data augmentation strategies for object detection. In European Conference on Computer Vision. Springer, 566--583.Google ScholarDigital Library
Index Terms
- A Gradient Balancing Approach for Robust Logo Detection
Recommendations
Robust Logo Detection in E-Commerce Images by Data Augmentation
MM '21: Proceedings of the 29th ACM International Conference on MultimediaLogo detection is an important task in the intellectual property protection in e-commerce. In the paper, we introduce our solution for the ACM MM2021 Robust Logo Detection Grand Challenge. The competition requires the detection of logos (515 categories) ...
Group Anomaly Detection Using Deep Generative Models
Machine Learning and Knowledge Discovery in DatabasesAbstractUnlike conventional anomaly detection research that focuses on point anomalies, our goal is to detect anomalous collections of individual data points. In particular, we perform group anomaly detection (GAD) with an emphasis on irregular group ...
Robust multi-logo watermarking by RDWT and ICA
Fractional calculus applications in signals and systemsThis paper proposes a new approach to watermarking multimedia products by redundant discrete wavelet transform (RDWT) and independent component analysis (ICA). For watermark security, embedded logo watermarks are encrypted to random noise signal. To ...
Comments