.png){kind=icon}
返回
End-to-end Point Supervised Object Detection with low-level instance features
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2024.111513.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The use of point-level annotations in Point Supervision Object Detection (PSOD) has gained popularity due to its low labeling cost and the provision of specific location information. Previous studies have often relied on Multiple Instance Learning (MIL) to select and refine a low-quality pseudo box, which heavily relies on category information. This method concentrates on identifying the most distinctive objects in each category within an image. However, without the boundary constraints provided by Ground-Truth (GT), the detector may suffer from instance ambiguity problems, which can significantly deteriorate the model's performance. To tackle these concerns, we propose an end-to-end object detection model called low-level instance features object detector (LIFOD) to mime low-level instance features information to refine the pseudo box. LIFOD utilizes a Low-level Feature Extractor (LFE) module to exploit low-level instance feature information to combine low-level feature information and category information, thus solving the challenge of instance ambiguity. To further alleviate the problem of local minima, we introduce bounding box regression in LIFOD and implement an end-toend training strategy for point-supervised models to mitigate local minima. We evaluate our proposed LIFOD method on the public datasets COCO 2014 and 2017 and show that it outperforms the existing image-level and point-level supervised detection methods, and significantly reduces the gap in performance between PSOD and box-level object detection.
Keyword:
End-to-end
Low-level instance features
Point supervision
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
Multicomponent Orbital-Optimized Perturbation Theory with Density Fitting: Anharmonic Zero-Point Energies in Protonated Water Clusters具有密度拟合的多组分轨道优化摄动理论: 质子化水团簇中的非谐零点能量
PREAI
分享收藏Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现.png)
Indoor Air
OAAI
Indoor AirIF0
OAAI分享收藏FePt–BN granular HAMR media with high grain aspect ratio and high L1 ordering on corning LotusTM NXT glassAIP Advances
OAAI
AIP AdvancesIF0
OAAI分享收藏分享收藏
查看更多内容