DeeSIL: Deep-Shallow Incremental Learning
Open accessIntegrity 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?
Fixed-representation based IL algorithms do not update the model but are less dependent on memory than fine-tuning based algorithms.
“We also present results with fixedrepresentation based algorithms [6, 23, 24, 56], which do not update the model but are also less dependent on memory.”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [6]
The use of external classifiers in DeeSIL is proposed because they are faster to optimize compared to an end-to-end FR.
“The use of external classifiers is proposed because they are faster to optimize compared to an end-to-end FR .”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [6]
If a larger pool of classes is available at the beginning of the process, the performance of fixed-representations will be boosted because the initial representation generalizes better.
“If a larger pool of classes is available at the beginning of the process, the performance of fixedrepresentations will be boosted because the initial representation generalizes better [6].”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [6]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
iCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988 · see citing works
Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem
McCloskey, M., & Cohen, N. J. (1989) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60536-8 · Cited by 3,770 · see citing works
Growing a Brain: Fine-Tuning by Increasing Model Capacity
Wang, Y.-X., Ramanan, D., & Hebert, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.323 · Cited by 154 · cited 1× · see citing works
“ood data representation when augmenting the number of tasks. However, it violates the third property of IL algorithms since its number of parameters increases with the number of tasks. The authors of [5] and [6] improve the plasticity of deep architectures by widening existing layers and/or deepening the network. Whil…”
Background
Flagged first, then by citations
Cited by
Sorted by citations
IL2M: Class Incremental Learning With Dual Memory
Belouadah, E., & Popescu, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00067 · Cited by 302 · see citing works
Self-citationA Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks
Belouadah, E., Popescu, A., & Kanellos, I. (2020) · arXiv · doi:10.48550/arxiv.2011.01844 · Cited by 235 · see citing works
“Yet another choice [4] is to exploit a fixed deep representation to extract features for all incremental states and a battery of linear SVMs to implement C .”
BackgroundMethodResultInfluentialSelf-citation
- Authors
- Belouadah, E., & Popescu, A.
- Affiliations
- Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR)
- Corresponding author
- Popescu, Adrian
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2019
- Volume
- 11130
- Pages
- 151-157
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2885561447
- Cited by
- 60
- References
- 4
- Citations by year
- 2026: 1 · 2025: 7 · 2024: 12 · 2023: 8 · 2022: 10 · 2021: 11 · 2020: 8 · 2019: 3
- FWCI
- 3.06
- Type
- conference paper
- Language
- en
- Open access
- green
- cea.hal.science
- Licence
- Locations
- Lecture notes in computer science (publishedVersion)
- HAL (submittedVersion, other-oa)
- 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 › Data Stream Mining Techniques
- Keywords
- incremental learning, catastrophic forgetting, transfer learning, shallow classifiers, deep feature extraction, limited memory, image classification
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
