• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) CAM°ú Selective Search¸¦ ÀÌ¿ëÇÑ È®ÀåµÈ °´Ã¼ Áö¿ªÈ­ ÇнÀµ¥ÀÌÅÍ »ý¼º ¹× ÀÌÀÇ ÀçÇнÀÀ» ÅëÇÑ WSOL ¼º´É °³¼±
¿µ¹®Á¦¸ñ(English Title) Expanded Object Localization Learning Data Generation Using CAM and Selective Search and Its Retraining to Improve WSOL Performance
ÀúÀÚ(Author) °í¼ö¿¬   ÃÖ¿µ¿ì   Sooyeon Go   Yeongwoo Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 10 NO. 09 PP. 0349 ~ 0358 (2021. 09)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù CAM[1]À» ÀÌ¿ëÇؼ­ À̹ÌÁöÀÇ °´Ã¼¿¡ ´ëÇÑ ÁÖÀÇ ¿µ¿ª ¶Ç´Â Áö¿ªÈ­(Localization) ¿µ¿ªÀ» ã´Â ¹æ¹ýÀÌ WSOLÀÇ ¿¬±¸·Î¼­ ´Ù¾çÇÏ°Ô ¼öÇàµÇ°í ÀÖ´Ù. CAMÀ» ÀÌ¿ëÇÑ °´Ã¼ÀÇ È÷Æ®(Heat) ¸Ê¿¡¼­ ÁÖÀÇ ¿µ¿ª ÃßÃâÀº °´Ã¼ÀÇ Æ¯Â¡ÀÌ °¡Àå ¸¹ÀÌ ¸ð¿© ÀÖ´Â ¿µ¿ª¸¸À» ÁÖ·Î ÁýÁßÇؼ­ °´Ã¼ÀÇ ÀüüÀûÀÎ ¿µ¿ªÀ» ãÁö ¸øÇÏ´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. ¿©±â¼­´Â À̸¦ °³¼±Çϱâ À§Çؼ­ ¸ÕÀú CAM°ú Selective Search[6]¸¦ ÇÔ²² ÀÌ¿ëÇÏ¿© CAM È÷Æ®¸ÊÀÇ ÁÖÀÇ ¿µ¿ªÀ» È®ÀåÇÏ°í, È®ÀåµÈ ¿µ¿ª¿¡ °¡¿ì½Ã¾È ½º¹«µùÀ» Àû¿ëÇÏ¿© ÀçÇнÀ µ¥ÀÌÅ͸¦ ¸¸µç ÈÄ, À̸¦ ÇнÀÇÏ¿© °´Ã¼ÀÇ ÁÖÀÇ ¿µ¿ªÀÌ È®ÀåµÇ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ¹æ¹ýÀº ´Ü ÇÑ ¹øÀÇ ÀçÇнÀ¸¸ÀÌ ÇÊ¿äÇϸç, ÇнÀ ÈÄ Áö¿ªÈ­¸¦ ¼öÇàÇÒ ¶§´Â Selective Search¸¦ ½ÇÇàÇÏÁö ¾Ê±â ¶§¹®¿¡ ó¸® ½Ã°£ÀÌ ´ëÆø ÁÙ¾îµç´Ù. ½ÇÇè¿¡¼­ ±âÁ¸ CAMÀÇ È÷Æ®¸Êµé°ú ºñ±³ÇßÀ» ¶§ ÇÙ½É Æ¯Â¡ ¿µ¿ªÀ¸·ÎºÎÅÍ ÁÖÀÇ ¿µ¿ªÀÌ È®ÀåµÇ°í, È®ÀåµÈ ÁÖÀÇ ¿µ¿ª ¹Ù¿îµù ¹Ú½º¿¡ ´ëÇÑ Ground Truth¿ÍÀÇ IOU °è»ê¿¡¼­ ±âÁ¸ CAMº¸´Ù ¾à 58%°¡ °³¼±µÇ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, a method of finding the attention area or localization area for an object of an image using CAM (Class Activation Map)[1] has been variously carried out as a study of WSOL (Weakly Supervised Object Localization). The attention area extraction from the object heat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where the features are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attention area in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the data to expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localization area is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expanded from the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding box of the expanded attention area, about 58% was improved compared to the existing CAM.
Å°¿öµå(Keyword) WSOL(Weakly Supervised Object Localization)   CAM(Class Activation Map)   ¼±ÅÃÀû Ž»ö   ÁÖÀÇ ¿µ¿ª   WSOL(Weakly Supervised Object Localization)   CAM(Class Activation Map)   Selective Search   Localization  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå