arrow
返回

Deep active learning with Weighting filter for object detection

delete2023-01-01
delete4
PRE
AI
W
Wei Huang *
S
Shuzhou Sun
林
林晓 (Xiao Lin) *
张
张达威 (Dawei Zhang)
马
马利庄 (Lizhuang Ma)
DOI:10.1016/j.displa.2022.102282delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Active learning has been demonstrated to be effective in reducing labeling costs by selecting the most valuable data from the unlabeled pool. However, the training data of the first epoch in almost all active learning methods is randomly selected, which will cause an instability learning process. Additionally, current active learning, especially uncertainty-based active learning methods, is prone to the problem of data bias because model learning inevitably prefers partial data. For the above issues, we propose Weighting filter (W-filter) tailored for object detection in this paper, which is an image filtering algorithm that can calculate the contribution of a single image to the neural network training as well as remove similar ones in the entire selected data to optimize the sampling results. We first use W-filter to select the training data of the first epoch, which can guarantee better performance and a more stable learning process. Then, we propose to resample the uncertain data from the perspective of the frequency domain to alleviate the problem of data bias. Finally, we redesign several classical uncertainty methods specifically for classification to make them more suitable for the task of object detection. We do rigorous experiments on standard benchmark datasets to validate our work. Several classical detectors such as Faster R-CNN, SSD, R-FCN, CenterNet, EfficientDet, and effective networks including ResNet, DarkNet, MobileNet are used in experiments, which shows our framework is detector-agnostic and network-agnostic and thus can meet any detection scenario.
Keyword:
Active learning
Object detection
Neural network

期刊

Displays 封面图
Displays
IF:
3.4
论文数:
2.3K
被引数:
3.2K

机构

S
Shanghai Normal University
学者数:
7.4K
论文数: 5.0K
被引数: 8.0K
引用论文

引用论文

The spectrum of somatic and germline NF1 mutations in NF1 patients with spinal neurofibromas
err2009-02-17
err0
PREAI
errMeena Upadhyaya; Gill Spurlock; Lan Kluwe; Nadia Chuzhanova; Emma Bennett; Nick Thomas; Abhijit Guha; Victor Mautner
err分享
err收藏
Optimization of the coherence properties of diamond samples with an intermediate concentration of NV centers
err2021-02-01
err0
errOAAI
errO.R. Rubinas; V.V. Soshenko; S.V. Bolshedvorskii; A.I. Zeleneev; A.S. Galkin; S.A. Tarelkin; S.Y. Troschiev; V.V. Vorobyov; V.N. Sorokin; A.A. Sukhanov; V.G. Vins; A.N. Smolyaninov; A.V. Akimov
err分享
err收藏
学者 查看更多内容