Learning without Forgetting

When building a unified vision system or gradually adding new apabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new ca...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2018-12, Vol.40 (12), p.2935-2947
Main Authors: Li, Zhizhong, Hoiem, Derek
Format: Article
Language:English
Subjects:
Artificial neural networks
Convolutional neural networks
Deep learning
Feature extraction
Knowledge engineering
Learning
Learning systems
multi-task learning
Neural networks
Retraining
Training
Training data
transfer learning
Tuning
Vision systems
Visual perception
visual recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:When building a unified vision system or gradually adding new apabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2017.2773081