주 객체 위치 검출을 위한 Grad-CAM 기반의 딥러닝 네트워크 = Grad-CAM based deep learning network for location detection of the main object

다국어 초록 (Multilingual Abstract)

In this paper, we propose an optimal deep learning network architecture for main object location detection through weak supervised learning. The proposed network adds convolution blocks for improving the localization accuracy of the main object through weakly-supervised learning. The additional deep learning network consists of five additional blocks that add a composite product layer based on VGG-16. And the proposed network was trained by the method of weakly-supervised learning that does not require real location information for objects. In addition, Grad-CAM to compensate for the weakness of GAP in CAM, which is one of weak supervised learning methods, was used. The proposed network was tested through the CUB-200-2011 data set, we could obtain 50.13% in top-1 localization error. Also, the proposed network shows higher accuracy in detecting the main object than the existing method.

참고문헌 (Reference)

1 K. Simonyan, "Very Deep Convolutional Networks for Large-Scale Image Recognition"

2 C. Wah, "The Caltech-UCSD Birds-200-2011 Dataset"

3 W. Liu, "SSD: Single Shot MultiBox Detector"

4 Y. Wei, "Object region mining with adversarial erasing: A simple classification to semantic segmentation approach"

5 M. Lin, "Network In Network"

6 B. Zhou, "Learning Deep Features for Discriminative Localization"

7 O. Russakovsky, "ImageNet Large Scale Visual Recognition Challenge"

8 K. K. Singh, "Hide-and-Seek: Forcing a network to be meticulous for weakly-supervised object and action localization"

9 R. R. Selvaraju, "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization"

10 J. Lee, "FickleNet:Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference"

11 S. Ren, "Faster R-CNN:towards real-time object detection with region proposal networks"

12 K. He, "Deep Residual Learning for Image Recognition"

13 X. Zhang, "Adversarial complementary learning for weakly supervised object localization"

14 J. Choe, "ADL:Attention-based Dropout Layer for Weakly Supervised Object Localization"