Lifelong Learning via Progressive Distillation and Retrospection
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Many incremental learning methods based on regularization save a small amount of old data to enhance model performance.
“Many incremental learning methods based on the regularization strategy save a small amount of old data to enhance model performance [47,70,76].”
From An Appraisal of Incremental Learning Methods (2020) · cites this paper as [70]
Experimental results prove that combining regularization strategy with rehearsal or pseudo-rehearsal strategy greatly helps improve model performance.
“The experimental results of [47,70,76] prove that the algorithm based on the regularization strategy is appropriately combined with a rehearsal or pseudo-rehearsal strategy, which is of great help to improve the performance of the model.”
From An Appraisal of Incremental Learning Methods (2020) · cites this paper as [70]
The DR method shows that keeping a small subset of old data has a significant effect on mitigating catastrophic forgetting.
“In addition, this method shows that keep a small subset of old data has a significant effect on mitigating the CF.”
From An Appraisal of Incremental Learning Methods (2020) · cites this paper as [70]
Many distillation strategy methods can only effectively mitigate catastrophic forgetting when the number of incremental tasks is small, and still difficult to meet long-term increments.
“Many distillation strategy methods can only effectively mitigate catastrophic forgetting when the number of incremental tasks is small, in which it is still difficult to meet the requirements of long-term increments [16,70,71].”
From An Appraisal of Incremental Learning Methods (2020) · cites this paper as [70]
Using similar experimental settings, the gap between results of three distillation-based methods is not obvious; this means soft label supervision has not been significantly enhanced, and using only new data is not reliable at present.
“Using similar experimental settings, the gap between the results of the three methods based on the distillation strategy is not too obvious [16,70,71]. This means that the supervision ability of soft labels has not been significantly enhanced, i.e., the method of using only new data is not reliable at present.”
From An Appraisal of Incremental Learning Methods (2020) · cites this paper as [70]
Only a small amount of old data needs to be retained to greatly alleviate catastrophic forgetting.
“On the one hand, only a small amount of old data needs to be retained to greatly alleviate CF [70,73].”
From An Appraisal of Incremental Learning Methods (2020) · cites this paper as [70]
The citation lists haven’t been fetched yet
References 27 · Cited by 190
- Authors
- Hou, S., Pan, X., Loy, C. C., Wang, Z., & Lin, D.
- Affiliations
- University of Science and Technology of China (CN)
- Chinese University of Hong Kong (HK)
- Nanyang Technological University (SG)
- Corresponding author
- Hou, Saihui
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2018
- Pages
- 452-467
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2895723011
- Cited by
- 190
- References
- 27
- Citations by year
- 2026: 5 · 2025: 17 · 2024: 31 · 2023: 23 · 2022: 28 · 2021: 42 · 2020: 30 · 2019: 13 · 2018: 1
- FWCI
- 8.67
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Lecture notes in computer science (publishedVersion)
- 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
- lifelong learning, knowledge distillation, retrospection, data caching, knowledge preservation, catastrophic forgetting, learning curve
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
