点击次数：
影响因子：5.779
DOI码：10.1016/j.neucom.2021.03.047
发表刊物：Neurocomputing
关键字：Weakly-supervised learning；Object detection；Empirical saliency Pseudo；ground-truth；Deep learning
摘要：Even though weakly-supervised object detection (WSOD) has become an effective method to relieve the heavy work of labeling, there are still difficult problems to be solved. WSOD method represented by a Multiple Instance Learning (MIL) have some common problems including running slowly and focusing on discriminative parts rather than the whole object, which will lead to false detection. To improve the efficiency and accuracy, we propose a single-shot weakly-supervised object detection model guided by empirical saliency model (SSWOD). As human vision always focuses on the most attracting parts of the image, saliency maps can usually guide our model to locate the most promising object areas. By this way, our model takes the saliency areas as pseudo ground-truths to realize the WSOD task with only class labels. Moreover, empirical saliency is designed to refine the pseudo ground-truth and improve the detection. Our new framework not only realizes a one-step detection without region proposals, but also reduces computational consumption. Experiments on PASCAL VOC 2007 & 2012 benchmarks demonstrate that SSWOD is 8 times faster and 5 times smaller than previous approaches, surpassing the state-of-the-art WSOD methods by 6.1% mean average precision (mAP). (c) 2021 Elsevier B.V. All rights reserved.
论文类型：期刊论文
一级学科：控制科学与工程
文献类型：期刊
卷号：455
页面范围：431-440
ISSN号：0925-2312
是否译文：否
发表时间：2021-09-30
收录刊物：SCI
发布期刊链接：https://linkinghub.elsevier.com/retrieve/pii/S0925231221004215