CoChat
Sign Up
Cited by 1,184Domain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsMachine Learning and Data Classification

End-to-End Incremental Learning

Open access
Castro, Francisco M., Marín-Jiménez, Manuel J., Guil, Nicolás, Schmid, Cordelia, Alahari, Karteek·2018·Lecture Notes in Computer Science
DOI 10.1007/978-3-030-01258-8_15
Open this paper in CoChat — free accountOpen PDF

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-030-01258-8_15

Cites

8 of 8 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • FT BAL is tributary to the fixed memory K because past exemplars are needed for the balancing step.

    “FT BAL is also tributary to the fixed memory K because past exemplars are needed for the balancing step.”

    From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [14]

    Section 4 (Incremental Learning; page not provided) says balanced fine-tuning uses equal numbers of samples from old and new classes, supporting the need for stored past exemplars. But Section 3.1 (Representative memory; page not provided) describes both a fixed-capacity memory K and a memory that grows with the number of classes. The balancing step therefore depends on past exemplars, not specifically on fixed memory K. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • Class IL algorithms provide the most interesting results in recent works from literature.

    “We focus on class IL algorithms which provide the most interesting results in recent works from literature [7, 8, 14, 23, 24, 28, 56, 75].”

    From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [14]

  • Herding-based exemplar selection was reported to provide only marginal improvement compared to random selection in prior work.

    “its usefulness was questioned in [14, 29, 37] where it was reported to provide only marginal improvement compared to random selection.”

    From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [14]

  • Sophisticated data augmentation in [14] has a small positive influence on results.

    “Sophisticated data augmentation is also used and has a small positive influence on results.”

    From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [14]

  • We run extensive experiments with both herding-based and random selection of exemplars and reach a different conclusion than [14,37].

    “We run extensive experiments with both methods and reach a different conclusion.”

    From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [14]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 25

  1. Ans, B., Rousset, S., French, R.M., Musca, S.: Self-refreshing memory in artificial neural networks: Learning temporal sequences without catastrophic forgetting. Connection Science 16(2), 71-99 (2004)
  2. Bengio, Y., Courville, A., Vincent, P.: Representation learning: A review and new perspec- tives. PAMI 35(8), 1798-1828 (2013)
  3. Cauwenberghs, G., Poggio, T.: Incremental and decremental support vector machine learn- ing. In: NIPS (2000)
  4. Chen, X., Shrivastava, A., Gupta, A.: NEIL: Extracting visual knowledge from web data. In: ICCV (2013)
  5. Divvala, S., Farhadi, A., Guestrin, C.: Learning everything about anything: Webly-supervised visual concept learning. In: CVPR (2014)
  6. French, R.M.: Dynamically constraining connectionist networks to produce distributed, or- thogonal representations to reduce catastrophic interference. In: Cognitive Science Society Conf. (1994)
  7. Furlanello, T., Zhao, J., Saxe, A.M., Itti, L., Tjan, B.S.: Active long term memory networks. ArXiv e-prints, arXiv 1606.02355 (2016) · arXiv
  8. Goodfellow, I., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. ArXiv e-prints, arXiv 1312.6211 (2013) · arXiv
  9. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS workshop (2014)
  10. Jung, H., Ju, J., Jung, M., Kim, J.: Less-forgetting learning in deep neural networks. ArXiv e-prints, arXiv 1607.00122 (2016) · arXiv
  11. Lopez-Paz, D., Ranzato, M.A.: Gradient episodic memory for continual learning. In: NIPS (2017)
  12. Mensink, T., Verbeek, J., Perronnin, F., Csurka, G.: Distance-based image classification: Generalizing to new classes at near-zero cost. PAMI 35(11), 2624-2637 (2013)
  13. Mitchell, T., Cohen, W., Hruschka, E., Talukdar, P., Betteridge, J., Carlson, A., Mishra, B.D., Gardner, M., Kisiel, B., Krishnamurthy, J., Lao, N., Mazaitis, K., Mohamed, T., Nakashole, N., Platanios, E., Ritter, A., Samadi, M., Settles, B., Wang, R., Wijaya, D., Gupta, A., Chen, X., Saparov, A., Greaves, M., Welling, J.: Never-ending learning. In: AAAI (2015)
  14. Neelakantan, A., Vilnis, L., Le, Q.V., Sutskever, I., Kaiser, L., Kurach, K., Martens, J.: Adding gradient noise improves learning for very deep networks. ArXiv e-prints, arXiv 1511.06807 (2017) · arXiv
  15. Ratcliff, R.: Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychological review 97(2), 285 (1990)
  16. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: NIPS (2015)
  17. Ristin, M., Guillaumin, M., Gall, J., Gool, L.V.: Incremental learning of ncm forests for large-scale image classification. In: CVPR (2014)
  18. Ruping, S.: Incremental learning with support vector machines. In: ICDM (2001)
  19. Rusu, A.A., Rabinowitz, N.C., Desjardins, G., Soyer, H., Kirkpatrick, J., Kavukcuoglu, K., Pascanu, R., Hadsell, R.: Progressive neural networks. ArXiv e-prints, arXiv 1606.04671 (2016) · arXiv
  20. Ruvolo, P., Eaton, E.: ELLA: An efficient lifelong learning algorithm. In: ICML (2013)
  21. Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)
  22. Thrun, S.: Lifelong Learning Algorithms, pp. 181-209. Springer US (1998)
  23. Vedaldi, A., Lenc, K.: MatConvNet -Convolutional Neural Networks for MATLAB. In: ACM Multimedia (2015)
  24. Welling, M.: Herding dynamical weights to learn. In: ICML (2009)
  25. Xiao, T., Zhang, J., Yang, K., Peng, Y., Zhang, Z.: Error-driven incremental learning in deep convolutional neural network for large-scale image classification. In: ACM Multimedia (2014)

Cited by

Sorted by citations

Authors
Castro, F. M., Marín-Jiménez, M. J., Guil, N., Schmid, C., & Alahari, K.
Affiliations
  • Universidad de Málaga (ES)
  • University of Córdoba (ES)
  • Institut polytechnique de Grenoble (FR)
Corresponding author
Castro, Francisco M.
ORCID
Venue
Lecture Notes in Computer Science
Publisher
Springer International Publishing
Published
2018
Volume
11216
Pages
241-257
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-030-01258-8_15
OpenAlex
W2884282566
Cited by
1,184
References
8
Citations by year
2026: 64 · 2025: 161 · 2024: 217 · 2023: 235 · 2022: 190 · 2021: 180 · 2020: 96 · 2019: 38 · 2018: 3
FWCI
32.35
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • HAL (submittedVersion, other-oa)
Funders
  • Nvidia
  • Indo-French Centre for the Promotion of Advanced Research
  • Junta de Andalucía (TIC-1692)
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 › Machine Learning and Data Classification
Keywords
catastrophic forgetting, incremental learning, continual learning, end-to-end learning, knowledge distillation, cross-entropy loss, 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