Overcoming Catastrophic Forgetting in Convolutional Neural Networks by Selective Network Augmentation

By Abel S. Zacarias, Luís A. Alexandre. 2018

14 citations recorded by the source corpus.

Lifelong learning aims to develop machine learning systems that can learn new tasks while preserving the performance on previous learned tasks. In this paper we present a method to overcome catastrophic forgetting on convolutional neural networks, that learns new tasks and preserves the performance on old tasks without accessing the data of the original model, by selective network augmentation (SeNA-CNN). The experiment results showed that SeNA-CNN, in some scenarios, outperforms the state-of-art Learning without Forgetting algorithm. Results also showed that in some situations it is better to use SeNA-CNN instead of training a neural network using isolated learning.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Taeyeong Kwak
2. Inyoung Paik
3. Sangjun Oh
4. Injung Kim

In Computer Vision and Pattern Recognition

1. Taeyeong Kwak
2. Inyoung Paik
3. Sangjun Oh
4. Injung Kim

Citations in the corpus

• Overcoming Catastrophic Forgetting by Neuron-level Plasticity Control (2019, background): “(Li and Hoiem 2018; Shin et al. 2017; Kamra, Gupta, and Liu 2017; Zacarias and Alexandre 2018; Kim, Kim, and Lee 2018) Another approach is to isolate the parts of the neural network containing previous knowledge, and learn the new task using other parts of the network.”