mlsanityData to 14 Oct 2026

DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning

arXiv 2403.17503 ↗First posted 26 Mar 2024cs.LG cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that retain access to past samples. In this paper, to solve the exemplar-free CIL problem, we propose a Dual-Stream Analytic Learning (DS-AL) approach. The DS-AL contains a main stream offering an analytical (i.e., closed-form) linear solution, and a compensation stream improving the inherent under-fitting limitation due to adopting linear mapping. The main stream redefines the CIL problem into a Concatenated Recursive Least Squares (C-RLS) task, allowing an equivalence between the CIL and its joint-learning counterpart. The compensation stream is governed by a Dual-Activation Compensation (DAC) module. This module re-activates the embedding with a different activation function from the main stream one, and seeks fitting compensation by projecting the embedding to the null space of the main stream's linear mapping. Empirical results demonstrate that the DS-AL, despite being an exemplar-free technique, delivers performance comparable with or better than that of replay-based methods across various datasets, including CIFAR-100, ImageNet-100 and ImageNet-Full. Additionally, the C-RLS' equivalent property allows the DS-AL to execute CIL in a phase-invariant manner. This is evidenced by a never-before-seen 500-phase CIL ImageNet task, which performs on a level identical to a 5-phase one. Our codes are available at https://github.com/ZHUANGHP/Analytic-continual-learning.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 7 of its 19 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

7 of 19 references.

References · 7

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2016Learning without Forgettingcited by 2,496
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  4. 2019Large Scale Incremental Learningcited by 732
  5. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 221
  6. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
  7. 2016Less-forgetting Learning in Deep Neural Networkscited by 97

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 15; 2026: 7.

28 papers.

Sort:

By area:

  1. 2024Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancementcited by 48
  2. 2024Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learningcited by 14
  3. 2025Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learningcited by 14
  4. 2024AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Modelscited by 11
  5. 2024AIR: Analytic Imbalance Rectifier for Continual Learningcited by 8
  6. 2024Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Taskcited by 4
  7. 2025Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learningcited by 3
  8. 2025OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensingcited by 2
  9. 2025Analytic Subspace Routing: How Recursive Least Squares Works in Continual Learning of Large Language Modelcited by 2
  10. 2025Holistic Continual Learning under Concept Drift with Adaptive Memory Realignmentcited by 2
  11. 2024TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learningcited by 1
  12. 2025OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaborationcited by 1
16 more
  1. 2025Forward-Only Continual Learningcited by 1
  2. 2025CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learningcited by 1
  3. 2025AL-GNN: Privacy-Preserving and Replay-Free Continual Graph Learning via Analytic Learningcited by 1
  4. 2026Analytic Drift Resister for Non-Exemplar Continual Graph Learningcited by 1
  5. 2026Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learningcited by 1
  6. 2025Continual learning via probabilistic exchangeable sequence modellingcited by 0
  7. 2025Gradient-Free Continual Learningcited by 0
  8. 2025Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculturecited by 0
  9. 2025MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learningcited by 0
  10. 2025Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learningcited by 0
  11. 2025Scalable Class-Incremental Learning Based on Parametric Neural Collapsecited by 0
  12. 2026Analytic Incremental Learning For Sound Source Localization With Imbalance Rectificationcited by 0
  13. 2026Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learningcited by 0
  14. 2026Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learningcited by 0
  15. 2026Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learningcited by 0
  16. 2026SPARCL: Spectral Partitioned Analytic Continual Learningcited by 0