.png){kind=icon}
返回
SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2023.3323793.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
By exploring the localizable representations in deep CNN, weakly supervised object localization (WSOL) methods could determine the position of the object in each image just trained by the classification task. However, the partial activation problem caused by the discriminant function makes the network unable to locate objects accurately. To alleviate this problem, we propose Structure-Preserved Attention Activated Network (SPA(2)Net), a simple and effective one-stage WSOL framework to explore the ability of structure preservation of deep features. Different from traditional WSOL approaches, we decouple the object localization task from the classification branch to reduce their mutual influence by involving a localization branch which is online refined by a self-supervised structural-preserved localization mask. Specifically, we employ the high-order self-correlation as structural prior to enhance the perception of spatial interaction within convolutional features. By succinctly combining the structural prior with spatial attention, activations by SPA(2)Net will spread from part to the whole object during training. To avoid the structure-missing issue caused by the classification network, we furthermore utilize the restricted activation loss (RAL) to distinguish the difference between foreground and background in the channel dimension. In conjunction with the self-supervised localization branch, SPA(2)Net can directly predict the class-irrelevant localization map while prompting the network to pay more attention to the target region for accurate localization. Extensive experiments on two publicly available benchmarks, including CUB-200-2011 and ILSVRC, show that our SPA(2)Net achieves substantial and consistent performance gains compared with baseline approaches. The code and models are available at https://github.com/MsterDC/SPA2Net.
Keyword:
High-order self-correlation
class activation map
structure preservation
weakly supervised object localization
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
Steroids for the treatment of corrosive esophageal injury: A statistical analysis of past studies
OAAI
OAAI分享收藏Molecular and Pharmacological Characterization of GABAA Receptors in the Rat Pituitary大鼠垂体中GABAA 受体的分子和药理学特征
PREAI
分享收藏
Local self-similarity-based registration of human ROIs in pairs of stereo thermal-visible videos.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容