Understand
Remarkable progress has been made in object instance detection and segmentation in recent years.
- However, existing state-of-the-art methods are mostly evaluated with fairly balanced and class-limited benchmarks, such as Microsoft COCO dataset [8].
- In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals.
- Based on this observation, we propose to calibrate the prediction of classification head to improve recognition performance for the tail classes.
Built on
Microsoft COCO: Common objects in context
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick · 2014
Earlier work this paper cites.
Mask r-cnn
Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick · 2017
Earlier work this paper cites.
COCO-Stuff: Thing and stuff classes in context
Holger Caesar, Jasper Uijlings, and Vittorio Ferrari · 2018
Earlier work this paper cites.
Similar
Cascade r-cnn: Delving into high quality object detection
Zhaowei Cai and Nuno Vasconcelos · 2018
Cited alongside, same era.
Hybrid task cascade for instance segmentation
Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, et al · 2019
Cited alongside, same era.
MMDetection: Open mmlab detection toolbox and benchmark
Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, and Dahua Lin · 2019
Cited alongside, same era.
Then
LVIS: A dataset for large vocabulary instance segmentation
Agrim Gupta, Piotr Dollar, and Ross Girshick · 2019
Closest in time.
Decoupling representation and classifier for long-tailed recognition
Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, and Yannis Kalantidis · 2019
Closest in time.
The devil is in classification: A simple framework for long-tail instance segmentation
Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Junhao Liew, Sheng Tang, Steven Hoi, and Jiashi Feng · 2020
Closest in time.
Beyond the bibliography
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…