Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Daisuke, Ueta"'
In this paper, we introduce a novel unbiased regression loss for DETR-based detectors. The conventional $L_{1}$ regression loss tends to bias towards larger boxes, as they disproportionately contribute more towards the overall loss compared to smalle
Externí odkaz:
http://arxiv.org/abs/2410.22638
