Active Weighted Mapping-based Residual Convolutional Neural Network for Image Classification
- 주제(키워드) Deep learning , Object recognition , Convolutional neural network , Residual convolutional network
- 발행기관 아주대학교
- 지도교수 황원준
- 발행년도 2021
- 학위수여년월 2021. 2
- 학위명 석사
- 학과 및 전공 일반대학원 인공지능학과
- 실제URI http://www.dcollection.net/handler/ajou/000000030621
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal weights. However, it is questionable whether it is correct to use the fixed and predefined weights at the mapping units of all paths. In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. The weight values of each mapping unit are not fixed but changed as the input image is changed, and the most proper weight values for each mapping unit are derived according to the input image. For this purpose, channel-wise information is embedded from both the shortcut connection and convolutional block, and then the fully connected layers are used to estimate the weight values for the mapping units. We train the backbone network and the proposed module alternately for a more stable learning of the proposed method. With extension to DenseNet, we propose the block selection method which reduce the burden on memory and improve performance. We verify the superiority and generality of the proposed method on various datasets in comparison with the baseline.
more목차
Ⅰ. Introduction 1
Ⅱ. Related Work 5
Ⅲ. Proposed Method 8
A. Active Weighted Mapping Module 9
B. Training Strategy 11
C. Block Selection Module 13
Ⅳ. Experimental Results and Discussion 16
A. Experimental Results for Cifar-10 and Cifar-100 datasets 16
B. Analysis on inferred weights 18
C. Comparison with well-known methods 20
D. Experimental results on ImageNet2012 dataset 21
E. Experimental Results: DenseNet on Cifar-10 dataset 22
Ⅴ. Conclusion 24
Reference 25
