ADINet: Attribute Driven Incremental Network for Retinal Image Classification
| Autor: | Satoh Shin'ichi, Qier Meng |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Forgetting Contextual image classification business.industry Computer science Entropy (statistical thermodynamics) Deep learning Knowledge engineering Feature extraction 02 engineering and technology Machine learning computer.software_genre Retinal image Entropy (classical thermodynamics) 020901 industrial engineering & automation Incremental learning 0202 electrical engineering electronic engineering information engineering Entropy (information theory) 020201 artificial intelligence & image processing Artificial intelligence Entropy (energy dispersal) business computer Entropy (arrow of time) Entropy (order and disorder) |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr42600.2020.00409 |
| Popis: | Retinal diseases encompass a variety of types, including different diseases and severity levels. Training a model with different types of disease is impractical. Dynamically training a model is necessary when a patient with a new disease appears. Deep learning techniques have stood out in recent years, but they suffer from catastrophic forgetting, i.e., a dramatic decrease in performance when new training classes appear. We found that keeping the feature distribution of an old model helps maintain the performance of incremental learning. In this paper, we design a framework named ``Attribute Driven Incremental Network" (ADINet), a new architecture that integrates class label prediction and attribute prediction into an incremental learning framework to boost the classification performance. With image-level classification, we apply knowledge distillation (KD) to retain the knowledge of base classes. With attribute prediction, we calculate the weight of each attribute of an image and use these weights for more precise attribute prediction. We designed attribute distillation (AD) loss to retain the information of base class attributes as new classes appear. This incremental learning can be performed multiple times with a moderate drop in performance. The results of an experiment on our private retinal fundus image dataset demonstrate that our proposed method outperforms existing state-of-the-art methods. For demonstrating the generalization of our proposed method, we test it on the ImageNet-150K-sub dataset and show good performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|