RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition

doi:doi:10.57702/hm8kfsf9

RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition

Fine-grained image recognition (FGIR) has been a challenging problem. Most of the current methods are dominated by convolutional neural networks (CNNs). FGIR has the problem of large intra-class variance and small inter-class variance. Therefore, FGIR methods need to be able to identify and localize region attention in an image that is critical for classification.

BibTex:

@dataset{Yunqing_Hu_and_Xuan_Jin_and_Yin_Zhang_and_Haiwen_Hong_and_Jingfeng_Zhang_and_Yuan_He_and_Hui_Xue_2024,
    abstract = {Fine-grained image recognition (FGIR) has been a challenging problem. Most of the current methods are dominated by convolutional neural networks (CNNs). FGIR has the problem of large intra-class variance and small inter-class variance. Therefore, FGIR methods need to be able to identify and localize region attention in an image that is critical for classification.},
    author = {Yunqing Hu and Xuan Jin and Yin Zhang and Haiwen Hong and Jingfeng Zhang and Yuan He and Hui Xue},
    doi = {10.57702/hm8kfsf9},
    institution = {No Organization},
    keyword = {'Fine-grained Image Recognition', 'Multi-scale Transformer', 'Region Attention'},
    month = {dec},
    publisher = {TIB},
    title = {RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition},
    url = {https://service.tib.eu/ldmservice/dataset/rams-trans--recurrent-attention-multi-scale-transformer-for-fine-grained-image-recognition},
    year = {2024}
}