Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment

Understand

Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples.

• Undoubtedly, this task inherits the main challenges from both few-shot learning and fine-grained recognition.
• First, the lack of labeled samples makes the learned model easy to overfit.
• Second, it also suffers from high intra-class variance and low inter-class differences in the datasets.