Pith. sign in

REVIEW 9 cited by

Class-Incremental Learning: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.03648 v2 pith:TLG4ZJGR submitted 2023-02-07 cs.CV cs.LG

Da-Wei Zhou , Qi-Wei Wang , Zhi-Hong Qi , Han-Jia Ye , De-Chuan Zhan , Ziwei Liu This is my paper · ORCID
classification cs.CVcs.LG
keywords learningclass-incrementalclassescomparisonmodelsurveybudgetcharacteristics
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs -- the model tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. There have been numerous efforts to tackle catastrophic forgetting in the machine learning community. In this paper, we survey comprehensively recent advances in class-incremental learning and summarize these methods from several aspects. We also provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms empirically. Furthermore, we notice that the current comparison protocol ignores the influence of memory budget in model storage, which may result in unfair comparison and biased results. Hence, we advocate fair comparison by aligning the memory budget in evaluation, as well as several memory-agnostic performance measures. The source code is available at https://github.com/zhoudw-zdw/CIL_Survey/

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Class Balance Matters to Active Class-Incremental Learning

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A distribution-matching, class-balanced selection method (CBS) improves incremental learning from unlabeled pools, beating random and standard active learning baselines on five datasets.

  2. TinySubNets: An efficient and low capacity continual learning strategy

    cs.LG 2024-12 conditional novelty 6.0 of 10

    TinySubNets combines per-layer pruning, adaptive quantization, and KL-gated weight sharing to run continual image classification with much lower memory than PackNet, WSN, and Ada-QPacknet.

  3. Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

    cs.LG 2025-07 conditional novelty 5.0 of 10

    DCE trains frequency-aware experts with complementary losses plus a Gaussian-sampled dynamic selector, reporting SOTA accuracy on four imbalanced domain-incremental benchmarks.

  4. A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning

    cs.LG 2025-05 conditional novelty 5.0 of 10

    UG-CLU derives a four-part gradient update for continual learning and unlearning and shows it outperforms task-level CLU methods on new fine-grained benchmarks.

  5. Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculture

    cs.LG 2025-04 conditional novelty 5.0 of 10

    A prototype-based audio-visual continual learning method, HAIL-FFIA, reaches 75.92% average accuracy on a new six-species fish-feeding dataset while storing only 0.1% of raw data.

  6. Learning Mamba as a Continual Learner: Meta-learning Selective State Space Models for Efficient Continual Learning

    cs.LG 2024-12 conditional novelty 5.0 of 10

    Mamba can be meta-learned as an efficient continual learner, matching or surpassing Transformers on meta-continual learning tasks with a fixed-size state and a selectivity regularizer.

  7. Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels

    cs.CV 2025-08 conditional novelty 4.0 of 10

    ICPL generates pseudo-labels by clustering embeddings with KMeans, keeps only confident ones, and uses them to train class-incremental models without human labels, losing about 10 points versus supervised CIL but beat...

  8. C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning

    cs.LG 2025-08 conditional novelty 4.0 of 10

    Adding zeroth- and first-order flatness penalties to continual learning losses yields small consistent accuracy gains across seven methods, with the gated C-Flat++ variant at roughly 30% of the update cost.

  9. Parameter-Efficient Continual Fine-Tuning: A Survey

    cs.LG 2025-04 conditional novelty 3.0 of 10

    A survey and comparison of Parameter-Efficient Continual Fine-Tuning methods for adapting large pre-trained models to sequential tasks without catastrophic forgetting.

Pith tools