.png){kind=icon}
返回
Attention Erasing and Instance Sampling for Weakly Supervised Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2023.3339956.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Weakly supervised object detection (WSOD) trains detectors by only weak labels, aiming to save the burden of expensive bounding box-level annotations. Most previous efforts formulate WSOD as a multiple instance learning (MIL) problem, which is prone to detect discriminative object parts and miss object instances. This article proposes an attention erasing and instance sampling (AE-IS) approach to alleviate the above problems. Concretely, we first apply an attention erasing (AE) scheme to the WSOD model to hide the most discriminative region for capturing the integral extent of the object. Then, we employ an intersection-over-union (IoU)-balanced sampling component toward mining more object instances. Moreover, an instance reweighted loss (IRL) is designed to learn a larger portion of object instances, thereby further enhancing the performance of the object detector. Experimental results demonstrate that our method significantly improves the baseline approach by great margins and achieves competitive performance with the state-of-the-art algorithms on the NWPU VHR-10.v2 (72.0% mAP, 76.1% CorLoc) and DIOR (29.1% mAP, 55.9% CorLoc) datasets. The source code will be available at https://github.com/XuanX/AE-IS.
Keyword:
Attention erasing (AE)
instance reweighted loss (IRL)
intersection-over-union (IoU)-balanced sampling
weakly supervised object detection (WSOD)
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
Hybrid SWOT Approach for Strategic Planning and Formulation in China Worldwide Express Mail Service
OAAI
OAAI分享收藏分享收藏分享收藏Revealing influencing factors on global waste distribution via deep-learning based dumpsite detection from satellite imagery.png)
NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images对光学遥感图像中目标检测的威胁性补丁攻击
OAAI
OAAI分享收藏Instance-Aware Distillation for Efficient Object Detection in Remote Sensing Images用于遥感图像中有效目标检测的实例感知蒸馏
PREAI
分享收藏
查看更多内容