.png){kind=icon}
Return
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}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
A contrario reasoning
One-class semantic segmentation
Deep learning
Convolutional neural networks
Small target detection
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSave
ShareSaveReduced tubulin tyrosination as an early marker of mercury toxicity in differentiating N2a cellsOAAI
OAAIShareSaveOptimal Policies for the Pricing and Replenishment of Fashion Apparel considering the Effect of Fashion Level.png)
ComplexityOAAI
ComplexityIF0
OAAIShareSaveShareSaveShareSave
View more