Attention Erasing and Instance Sampling for Weakly Supervised Object Detection

doi:10.1109/TGRS.2023.3339956

Attention Erasing and Instance Sampling for Weakly Supervised Object Detection

2024-01-01

16

PRE

AI

DOI：10.1109/TGRS.2023.3339956

Original

Original request for help

Save

Abstract

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.

Keywords:

Attention erasing (AE)

instance reweighted loss (IRL)

intersection-over-union (IoU)-balanced sampling

weakly supervised object detection (WSOD)

Attention Erasing and Instance Sampling for Weakly Supervised Object Detection

Abstract

Journal

Organization