CAM과 Selective Search를 이용한 확장된객체 지역화 학습데이터 생성 및 이의 재학습을 통한 WSOL 성능 개선
Expanded Object Localization Learning Data Generation Using CAM and Selective Search and Its Retraining to Improve WSOL Performance
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 CAM[1]을 이용해서 이미지의 객체에 대한 주의 영역 또는 지역화(Localization) 영역을 찾는 방법이 WSOL의 연구로서 다양하게 수행되고있다. CAM을 이용한 객체의 히트(Heat) 맵에서 주의 영역 추출은 객체의 특징이 가장 많이 모여 있는 영역만을 주로 집중해서 객체의 전체적인영역을 찾지 못하는 단점이 있다. 여기서는 이를 개선하기 위해서 먼저 CAM과 Selective Search[6]를 함께 이용하여 CAM 히트맵의 주의 영역을확장하고, 확장된 영역에 가우시안 스무딩을 적용하여 재학습 데이터를 만든 후, 이를 학습하여 객체의 주의 영역이 확장되는 방법을 제안한다. 제안 방법은 단 한 번의 재학습만이 필요하며, 학습 후 지역화를 수행할 때는 Selective Search를 실행하지 않기 때문에 처리 시간이 대폭 줄어든다. 실험에서 기존 CAM의 히트맵들과 비교했을 때 핵심 특징 영역으로부터 주의 영역이 확장되고, 확장된 주의 영역 바운딩 박스에 대한 GroundTruth와의 IOU 계산에서 기존 CAM보다 약 58%가 개선되었다.
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 objectheat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where thefeatures are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attentionarea in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the datato expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localizationarea is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expandedfrom the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding boxof the expanded attention area, about 58% was improved compared to the existing CAM.
참고문헌 (15)
- B. Zhou, "Learning deep features for discriminative localization", Computer Vision and Pattern Recognition, pp.2921~2929 (2016)
- X. Zhang, "Adversarial complementary learning for weakly supervised object localization", IEEE Computer Vision and Pattern Recognition,, pp.1325~1334 (2018)
- K. K. Singh, "Hide-and-seek : Forcing a network to be meticulous for weakly-supervised object and action localization", arXiv preprint arXiv : 1704. 04232, ~ (2017)
- S. Yun, "Cutmix : Regularization strategy to train strong classifiers with localizable features", International Conference on Computer Vision, pp.6022~6031 (2019)
- X. Zhang, "Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps", Computer Vision and Pattern Recognition (2020)
- J. Uijlings, "Selective search for object recognition", International Computer of Computer Vision, 104, pp.154~171 (2013)
- L. Bazzani, "Self-taught object localization with deep networks", 2016IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE (2016)
- A. J. Bency, "Weakly supervised localization using deep feature maps", European Conference on Computer Vision, pp.714~731 (2016), Springer
- D. Li, "Weakly supervised object localization with progressive domain adaption", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
- P. Felzenszwalb, "Efficient graph-based image segmentation", International Journal of Computer Vision, 59(2) (2004)
- J. Redmon, "You only look once: Unified, real-time object detection" (2016), Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
- S. Ren, "Faster r-cnn : Towards real-time object detection with region proposal networks", Advances in Neural Information Processing Systems, 39, pp.1137~1149 (2015)
- A. Kolesnikov, "Seed, expand and constrain : Three principles for weakly-supervised image segmentation", European Conference on Computer Vision, pp.695~711 (2016)
- J. Deng, "Imagenet : A large-scale hierarchical image database", Conference on Computer Vision and Pattern Recognition, pp.248~255 (2009)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)