Skip to footer
Home Research Artificial Intelligence / Machine Learning Incremental Few-Shot Learning with Attention Attractor Networks

Incremental Few-Shot Learning with Attention Attractor Networks



This paper addresses the problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes; and several extra novel classes are being considered, each with only a few labeled examples. The model is then evaluated on the overall performance of both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Network, which regularizes the learning of novel classes. In each episode, we train a set of new weights to recognize novel classes until they converge. We demonstrate that the learned attractor network can recognize novel classes while remembering old classes, outperforming baselines that do not rely on an iterative optimization process.


Mengye Ren, Renjie Liao, Ethan Fetaya, Richard S. Zemel


Meta Learning workshop @ NeurIPS 2018

Full Paper

‘Incremental Few-Shot Learning with Attention Attractor Networks’ (PDF)

Uber ATG

Previous article Efficient Graph Generation with Graph Recurrent Attention Networks
Next article Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
Mengye Ren is a research scientist at Uber ATG Toronto. He is also a PhD student in the machine learning group of the Department of Computer Science at the University of Toronto. He studied Engineering Science in his undergrad at the University of Toronto. His research interests are machine learning, neural networks, and computer vision. He is originally from Shanghai, China.
Renjie Liao is a PhD student in Machine Learning Group, Department of Computer Science, University of Toronto, supervised by Prof. Raquel Urtasun and Prof. Richard Zemel. He is also a Research Scientist in Uber Advanced Technology Group Toronto. He is also affiliated with Vector Institute. He received M.Phil. degree from Department of Computer Science and Engineering, Chinese University of Hong Kong, under the supervision of Prof. Jiaya Jia. He got B.Eng. degree from School of Automation Science and Electrical Engineering in Beihang University (former Beijing University of Aeronautics and Astronautics).