Please use this identifier to cite or link to this item:
Title: Low-shot Object Detection via Classification Refinement.
Authors: Li, Yiting 
Cheng, Yu
Liu, Lu
Tian, Sichao
Zhu, Haiyue
Xiang, Cheng
Vadakkepat, Prahlad
Teo, Chek Sing
Lee, Tong Heng 
Keywords: Computer Vision and Pattern Recognition
Issue Date: 6-May-2020
Citation: Li, Yiting, Cheng, Yu, Liu, Lu, Tian, Sichao, Zhu, Haiyue, Xiang, Cheng, Vadakkepat, Prahlad, Teo, Chek Sing, Lee, Tong Heng (2020-05-06). Low-shot Object Detection via Classification Refinement.. CoRR abs/2005.02641. ScholarBank@NUS Repository.
Abstract: This work aims to address the problem of low-shot object detection, where only a few training samples are available for each category. Regarding the fact that conventional fully supervised approaches usually suffer huge performance drop with rare classes where data is insufficient, our study reveals that there exists more serious misalignment between classification confidence and localization accuracy on rarely labeled categories, and the prone to overfitting class-specific parameters is the crucial cause of this issue. In this paper, we propose a novel low-shot classification correction network (LSCN) which can be adopted into any anchor-based detector to directly enhance the detection accuracy on data-rare categories, without sacrificing the performance on base categories. Specially, we sample false positive proposals from a base detector to train a separate classification correction network. During inference, the well-trained correction network removes false positives from the base detector. The proposed correction network is data-efficient yet highly effective with four carefully designed components, which are Unified recognition, Global receptive field, Inter-class separation, and Confidence calibration. Experiments show our proposed method can bring significant performance gains to rarely labeled categories and outperforms previous work on COCO and PASCAL VOC by a large margin.
Source Title: CoRR
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
2005.02641v1.pdf488.26 kBAdobe PDF



Page view(s)

checked on Jan 15, 2021


checked on Jan 15, 2021

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.