# Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning

arXiv: https://arxiv.org/abs/2412.18219 · HTML: https://mlsanity.com/paper/2412.18219/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 59 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark](https://mlsanity.com/paper/1910.04867/) (2019)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)

## Built on by (most cited first, 18 of 18)

- [MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging](https://mlsanity.com/paper/2505.11883/) (2025)
- [CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning](https://mlsanity.com/paper/2507.09471/) (2025)
- [Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2508.01225/) (2025)
- [Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection](https://mlsanity.com/paper/2510.00303/) (2025)
- [Continual Knowledge Consolidation LORA for Domain Incremental Learning](https://mlsanity.com/paper/2510.16077/) (2025)
- [Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning](https://mlsanity.com/paper/2511.17201/) (2025)
- [One Adapter for All: Towards Unified Representation in Step-Imbalanced Class-Incremental Learning](https://mlsanity.com/paper/2603.10237/) (2026)
- [Sculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2508.05094/) (2025)
- [Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning](https://mlsanity.com/paper/2511.12090/) (2025)
- [Dual-Imbalance Continual Learning for Real-World Food Recognition](https://mlsanity.com/paper/2603.29133/) (2026)
- [SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2604.27596/) (2026)
- [SR2-LoRA: Self-Rectifying Inter-layer Relations in Low-Rank Adaptation for Class-Incremental Learning](https://mlsanity.com/paper/2605.07420/) (2026)
- [Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning](https://mlsanity.com/paper/2605.13835/) (2026)
- [Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning](https://mlsanity.com/paper/2605.29592/) (2026)
- [Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation](https://mlsanity.com/paper/2606.30190/) (2026)
- [Neural-Collapse-guided Task-Free Continual Anomaly Detection](https://mlsanity.com/paper/2609.03406/) (2026)
- [The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations](https://mlsanity.com/paper/2609.18560/) (2026)
- [Visual Branch is What You Need for CLIP-based Class-Incremental Learning](https://mlsanity.com/paper/2609.37888/) (2026)

## Abstract (arXiv)

We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods involve a trade-off between inference time and accuracy, ACMap consolidates task-specific adapters into a single adapter, thus achieving constant inference time across tasks without sacrificing accuracy. The framework employs adapter merging to build a shared subspace that aligns task representations and mitigates forgetting, while centroid prototype mapping maintains high accuracy by consistently adapting representations within the shared subspace. To further improve scalability, an early stopping strategy limits adapter merging as tasks increase. Extensive experiments on five benchmark datasets demonstrate that ACMap matches state-of-the-art accuracy while maintaining inference time comparable to the fastest existing methods. The code is available at https://github.com/tf63/ACMap.