Tiny object detection

doi:doi:10.57702/w7qyl0xe

Tiny object detection

Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios. However, existing tiny object detection methods use standard deep neural networks as their backbone architecture. We argue that such backbones are inappropriate for detecting tiny objects as they are designed for the classiﬁcation of larger objects, and do not have the spatial resolution to identify small targets.

BibTex:

@dataset{Yu_et_al_and_Gong_et_al_and_Jiang_et_al_and_Zhang_et_al_and_Liu_et_al_and_Tian_et_al_and_Tong_and_Wu_2024,
    abstract = {Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios. However, existing tiny object detection methods use standard deep neural networks as their backbone architecture. We argue that such backbones are inappropriate for detecting tiny objects as they are designed for the classiﬁcation of larger objects, and do not have the spatial resolution to identify small targets.},
    author = {Yu et al. and Gong et al. and Jiang et al. and Zhang et al. and Liu et al. and Tian et al. and Tong and Wu},
    doi = {10.57702/w7qyl0xe},
    institution = {No Organization},
    keyword = {'Object Detection', 'Tiny Object Detection'},
    month = {dec},
    publisher = {TIB},
    title = {Tiny object detection},
    url = {https://service.tib.eu/ldmservice/dataset/tiny-object-detection},
    year = {2024}
}