A new approach to training more interpretable model with additional segmentation

다국어 초록 (Multilingual Abstract)

It is not straightforward to understand how the complicated deep learning models work because they are almost black boxes. To address this problem, various approaches have been developed to provide interpretability and applied in black-box deep learning models. However, the traditional interpretable machine learning only helps us to understand the models which have already been trained. Therefore, if the models are not properly trained, it is obvious that the interpretable machine learning will not work well. We propose a simple but effective method which trains models to improve interpretability for image classification. We also evaluate how well the models focus on appropriate objects, not just relying on classification accuracy. We use Class Activation Mapping (CAM) to train and evaluate the model interpretability. As a result, with VOC PASCAL 2012 datasets, when the ResNet50 model is trained by the proposed approach the 0.5IOU is 29.61%, while the model which is trained only by images and labels is 13.00%. The classification accuracy of the proposed approach is 75.03%, the existing method is 68.38%, and FCN is 60.69%. These evaluations show that the proposed approach is effective.

국문 초록 (Abstract)

일반적인 딥러닝 모델은 작동 원리를 이해하기 쉽지 않다. 이 문제를 해결하기 위해 해석가능한 머신러닝 기법이 등장하였으며 모델에 적용할 수 있게 되었다. 그러나 기존 해석가능한 머신러닝은 이미 훈련된 모델을 이해하는데 사용된다. 본 논문은 이미지 분류에 대한 성능을 향상시키기 위해 모델을 학습시킬 때 해석가능한 머신러닝을 활용하는 방법을 제안한다. 우리는 CAM(Class Activation Mapping)을 사용하여 모델 해석 가능성을 학습하고 분류 정확도와 해석성을 평가한다. VOC PASCAL 2012 데이터셋 이미지와 라벨로만 학습한 기존 방법의 경우 분류 정확도 68.38%, 0.5IOU 13.00%인 반면, 제안한 기법을 적용하였을 때 분류 정확도 75.05%, 0.5IOU 29.61%로 모든 성능이 향상되어 제안한 방법이 효과적이라는 것을 보여준다.

목차 (Table of Contents)

• ABSTRACT i
• 국문 초록 ii
• ACKNOWLEDMENTS ii
• TABLE OF CONTENTS iv
• LIST OF TABLES v
• LIST OF FIGURES vi
• CHAPTER 1. INTRODUCTION 1
• CHAPTER 2. Related Work 3
• 2.1 CAM & Grad-CAM 3
• 2.2 GAIN 4
• 2.3 Differences between interpretable model and semantic segmentation training 5
• CHAPTER 3. Proposed Approach 6
• CHAPTER 4. Experiment 10
• 4.1 Dataset and model 10
• 4.2 Evaluation metrics 10
• 4.3 MNIST 12
• 4.4 Dogs and cats 14
• 4.5 PASCAL VOC 2012 16
• CHAPTER 5. Discussion 21
• CHAPTER 6. Conclusion 22
• REFERENCES 23