.png){kind=icon}
返回
Deep-NFA: A deep a contrario framework for tiny object detection
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2024.110312.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The detection of tiny objects is a challenging task in computer vision. Conventional object detection methods have difficulties in finding the balance between high detection rate and low false alarm rate. In the literature, some methods have addressed this issue by enhancing the feature map responses for small objects, but without guaranteeing robustness with respect to the number of false alarms induced by background elements. To tackle this problem, we introduce an a contrario decision criterion into the learning process to take into account the unexpectedness of tiny objects. This statistic criterion enhances the feature map responses while controlling the number of false alarms (NFA) and can be integrated as an add-on into any semantic segmentation neural network. Our add-on NFA module not only allows us to obtain competitive results for small target, road crack and ship detection tasks respectively, but also leads to more robust and interpretable results.
Keyword:
A contrario reasoning
One-class semantic segmentation
Deep learning
Convolutional neural networks
Small target detection
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏
Reduced tubulin tyrosination as an early marker of mercury toxicity in differentiating N2a cellsOAAI
OAAI分享收藏Optimal Policies for the Pricing and Replenishment of Fashion Apparel considering the Effect of Fashion Level.png)
ComplexityOAAI
ComplexityIF0
OAAI分享收藏
查看更多内容