Combinational class activation maps for weakly supervised object localization약지도 물체 위치 검출을 위한 클래스 활성화 지도 조합

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 71
  • Download : 0
Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previous methods utilize the activation map corresponding to the highest activation source. Exploiting only one activation map of the highest probability class is often biased into limited regions or sometimes even highlights background regions. To resolve these limitations, we propose to use activation maps, named combinational class activation maps (CCAM), which are linear combinations of activation maps from the highest to the lowest probability class. By using CCAM for localization, we suppress background regions to help highlighting foreground objects more accurately. In addition, we design the network architecture to consider spatial relationships for localizing relevant object regions. Specifically, we integrate non-local modules into an existing base network at both low- and high-level layers. Our final model, named non-local combinational class activation maps (NL-CCAM), obtains superior performance compared to previous methods on representative object localization benchmarks including ILSVRC 2016 and CUB-200-2011. Furthermore, we show that the proposed method has a great capability of generalization by visualizing other datasets.
Advisors
Kim, Changickresearcher김창익researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2021
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[iv, 41 p. :]

Keywords

Deep learning▼aWeakly supervised learning▼aObject localization▼aWeakly supervised object localization▼aClass activation maps; 딥러닝▼a약지도학습▼a물체 위치 검출▼a약지도 물체 위치 검출▼a클래스 활성화 지도

URI
http://hdl.handle.net/10203/295959
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948717&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0