DeepCollaboration: Collaborative Generative and Discriminative Models for Class Incremental Learning

Authors

  • Bo Cui Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences
  • Guyue Hu Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences
  • Shan Yu Brainnetome Center and NLPR;University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences School of Future Technology, University of Chinese Academy of Sciences

Keywords:

Object Detection & Categorization, (Deep) Neural Network Algorithms

Abstract

An important challenge for neural networks is to learn incrementally, i.e., learn new classes without catastrophic forgetting. To overcome this problem, generative replay technique has been suggested, which can generate samples belonging to learned classes while learning new ones. However, such generative models usually suffer from increased distribution mismatch between the generated and original samples along the learning process. In this work, we propose DeepCollaboration (D-Collab), a collaborative framework of deep generative and discriminative models to solve this problem effectively. We develop a discriminative learning model to incrementally update the latent feature space for continual classification. At the same time, a generative model is introduced to achieve conditional generation using the latent feature distribution produced by the discriminative model. Importantly, the generative and discriminative models are connected through bidirectional training to enforce cycle-consistency of mappings between feature and image domains. Furthermore, a domain alignment module is used to eliminate the divergence between the feature distributions of generated images and real ones. This module together with the discriminative model can perform effective sample mining to facilitate incremental learning. Extensive experiments on several visual recognition datasets show that our system can achieve state-of-the-art performance.

Downloads

Published

2021-05-18

How to Cite

Cui, B., Hu, G., & Yu, S. (2021). DeepCollaboration: Collaborative Generative and Discriminative Models for Class Incremental Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1175-1183. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16204

Issue

Section

AAAI Technical Track on Computer Vision I