• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) °´Ã¼ ŽÁö¿¡¼­ÀÇ È¿À²ÀûÀÎ ¿¹Ãø ¹Ú½º ȸ±Í ÇнÀÀ» À§ÇÑ µÑ·¹ ±â¹Ý IoU ¼Õ½ÇÇÔ¼ö
¿µ¹®Á¦¸ñ(English Title) A Perimeter-Based IoU Loss for Efficient Bounding Box Regression in Object Detection
ÀúÀÚ(Author) ±èÇöÁØ   ÃÖµ¿¿Ï   Hyun-Jun Kim   Dong-Wan Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 08 PP. 0913 ~ 0919 (2021. 08)
Çѱ۳»¿ë
(Korean Abstract)
ÀϹÝÀûÀ¸·Î °´Ã¼ ŽÁö¸¦ À§ÇÑ ½Å°æ¸ÁÀ» ÇнÀ½ÃÅ°±â À§Çؼ­´Â Ŭ·¡½º ºÐ·ù¿Í ¿¹Ãø ¹Ú½ºÀÇ È¸±Í ¼Õ½Ç ÇÔ¼ö¸¦ °áÇÕ ÇнÀÇÑ´Ù. ÇÏÁö¸¸ ±âÁ¸ ȸ±Í ¼Õ½Ç ÇÔ¼ö´Â ¿¹Ãø ¹Ù¿îµù ¹Ú½º¿Í Ÿ±ê ¹Ú½ºÀÇ °ãħÀ» ÃøÁ¤ÇÏ´Â µ¥ ¾²ÀÌ´Â IoU¿ÍÀÇ »ó°ü°ü°è°¡ Å©Áö ¾Ê¾Æ °´Ã¼ ŽÁö¿¡ ±×´ë·Î »ç¿ëÇϱ⿡´Â ÇÑ°è°¡ ÀÖ´Ù. ÀÌ¿¡ ȸ±ÍÀÇ ÃÖÀûÈ­¸¦ µ½±â À§ÇÑ Æä³ÎƼ Ç×(penalty term)À» ȸ±Í ¼Õ½Ç ÇÔ¼öÀÎ IoU Loss¿¡ Ãß°¡ÇÏ´Â ¿¬±¸°¡ ÁøÇàµÇ¾ú´Ù. ÇÏÁö¸¸ ÇØ´ç Æä³ÎƼ Ç×À¸·Î´Â ¹Ú½ºµéÀÌ ÇϳªÀÇ ¹Ú½º°¡ ´Ù¸¥ ¹Ú½º¸¦ Æ÷ÇÔÇϰųª Áß°£ Á¡ÀÌ °ãÄ¡¸é °ªÀÌ 0ÀÌ µÇ´Â °æ¿ì°¡ À־ IoU°¡ ÃÖÀûÈ­µÇ´Â µ¥ ÇÑ°è°¡ ÀÖ´Ù. À̸¦ º¸¿ÏÇϱâ À§ÇØ º» ³í¹®¿¡¼­´Â ¿¹Ãø ¹Ú½º¿Í Ÿ±ê ¹Ú½º¸¦ °¨½Î´Â ¿µ¿ª°ú Ÿ±ê ¹Ú½º¿Í ¿¹Ãø ¹Ú½º °¢°¢ÀÇ µÑ·¹ Â÷À̸¦ ÀÌ¿ëÇÑ »õ·Î¿î ȸ±Í ¼Õ½Ç ÇÔ¼ö, Perimeter IoU Loss¸¦ Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÑ ¹æ¹ýÀ» Àû¿ëÇÑ °á°ú ¿©·¯ °´Ã¼ ŽÁö ¸ðµ¨À» ÀÌ¿ëÇÑ ½ÇÇè°ú ¸ðÀǽÇÇèÀ» ÅëÇÏ¿© Perimeter IoU Loss°¡ ´Ù¸¥ ȸ±Í ¼Õ½Ç ÇÔ¼öº¸´Ù ´õ ³ôÀº Á¤È®µµ¸¦ º¸ÀÓÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In object detection, neural networks are generally trained by minimizing two types of losses simultaneously, namely classification loss and regression loss for bounding boxes. However, the regression loss often fails to achieve its ultimate goal, that is, it often obtains a predicted bounding box that maximally intersects with its target box. This is due to the fact that the regression loss is not highly correlated with the IoU, which actually measures how much the bounding box and its target box overlap with each other. Although several penalty terms have been invented and added to the IoU loss in order to address the problem of regression losses, they still show some inefficiency particularly when penalty terms become zero by enclosing another box or overlapping with the center point before the bounding box and its target box are perfectly the same. In this paper, we propose a perimeter based IoU (PIoU) loss exploiting the perimeter differences of the minimum bounding rectangle of both a predicted box and its target box from those of two boxes themselves. In our experiments using the state-of-the-art object detection models (e.g., YOLO v3, SSD, and FCOS), we show that our PIoU loss consistently achieves better accuracy than all the other existing IoU losses.
Å°¿öµå(Keyword) °´Ã¼ ŽÁö   ¿¹Ãø ¹Ú½º ȸ±Í   IoU ¼Õ½Ç ÇÔ¼ö   Á¤Ä¢È­   object detection   bounding box regression   IoU Loss function   regularization  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå