Less-Forgetful Learning for Domain Expansion in Deep Neural Networks
Open accessAbstract
Expanding the domain that deep neural network has already learned without accessing old domain data is a challenging task because deep neural networks forget previously learned information when learning new data from a new domain. In this paper, we propose a less-forgetful learning method for the domain expansion scenario. While existing domain adaptation techniques solely focused on adapting to new domains, the proposed technique focuses on working well with both old and new domains without needing to know whether the input is from the old or new domain. First, we present two naive approaches which will be problematic, then we provide a new method using two proposed properties for less-forgetful learning. Finally, we prove the effectiveness of our method through experiments on image classification tasks. All datasets used in the paper, will be released on our website for someone's follow-up study.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The KT method requires an equal number of categories in the old and new tasks.
“However, this requires an equal number of categories in the old and new tasks.”
From An Appraisal of Incremental Learning Methods (2020) · cites this paper as [75]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 23 · Cited by 75
Research works printed but not linked: 4
- Goodfellow, I. J.; Mirza, M.; Xiao, D.; Courville, A.; and Bengio, Y. 2013a. An empirical investigation of catastrophic forgeting in gradient-based neural networks. arXiv preprint arXiv:1312.6211 . · arXiv
- Goodfellow, I. J.; Warde-Farley, D.; Mirza, M.; Courville, A.; and Bengio, Y. 2013b. Maxout networks. In International Conference on Machine Learning (ICML) .
- Shin, H.; Lee, J. K.; Kim, J.; and Kim, J. 2017. Continual learning with deep generative replay. arXiv preprint arXiv:1705.08690 . · arXiv
- Srivastava, R. K.; Masci, J.; Kazerounian, S.; Gomez, F.; and Schmidhuber, J. 2013. Compete to compute. In Advances in Neural Information Processing Systems (NIPS) , 2310-2318.
- Authors
- Jung, H., Ju, J., Jung, M., & Kim, J.
- Affiliations
- Korea Advanced Institute of Science and Technology (KR)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-29
- Volume
- 32
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2963178577
- Cited by
- 75
- References
- 23
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 6 · 2023: 10 · 2022: 15 · 2021: 12 · 2020: 12 · 2019: 9 · 2018: 3
- FWCI
- 3.66
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Ministry of Science and ICT, South Korea
- LG Electronics
- Institute for Information and Communications Technology Promotion (2016-0-00563)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- domain expansion, catastrophic forgetting, domain adaptation, continual learning, image classification, deep neural network
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
