ملف الباحث

Na Dong

ورقة واحدة في مجموعة PaperMetrix

المنشورات

أوراق هذا المؤلف

  1. Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data

    2023 · arXiv (Cornell University)

    Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise learning framework to …