# SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training

arXiv: https://arxiv.org/abs/2408.08295 · HTML: https://mlsanity.com/paper/2408.08295/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 73 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 30 of 57)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)

## Built on by (most cited first, 10 of 10)

- [A Practitioner's Guide to Continual Multimodal Pretraining](https://mlsanity.com/paper/2408.14471/) (2024)
- [MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2506.09105/) (2025)
- [Domain Generalizable Continual Learning](https://mlsanity.com/paper/2510.16914/) (2025)
- [DUKAE: DUal-level Knowledge Accumulation and Ensemble for Pre-Trained Model-Based Continual Learning](https://mlsanity.com/paper/2504.06521/) (2025)
- [Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning](https://mlsanity.com/paper/2505.12318/) (2025)
- [T2I-ConBench: Text-to-Image Benchmark for Continual Post-training](https://mlsanity.com/paper/2505.16875/) (2025)
- [Frugal Incremental Generative Modeling using Variational Autoencoders](https://mlsanity.com/paper/2505.22408/) (2025)
- [Deep Generative Continual Learning using Functional LoRA: FunLoRA](https://mlsanity.com/paper/2510.02631/) (2025)
- [Scalable Analytic Classifiers with Associative Drift Compensation for Class-Incremental Learning of Vision Transformers](https://mlsanity.com/paper/2602.00144/) (2026)
- [SPARCL: Spectral Partitioned Analytic Continual Learning](https://mlsanity.com/paper/2608.21307/) (2026)

## Abstract (arXiv)

In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trained models (PTMs) can greatly facilitate knowledge transfer and alleviate catastrophic forgetting, but also suffers from progressive overfitting of pre-trained knowledge into specific downstream tasks. A majority of current efforts often keep the PTMs frozen and incorporate task-specific prompts to instruct representation learning, coupled with a prompt selection process for inference. However, due to the limited capacity of prompt parameters, this strategy demonstrates only sub-optimal performance in continual learning. In comparison, tuning all parameters of PTMs often provides the greatest potential for representation learning, making sequential fine-tuning (Seq FT) a fundamental baseline that has been overlooked in CLPT. To this end, we present an in-depth analysis of the progressive overfitting problem from the lens of Seq FT. Considering that the overly fast representation learning and the biased classification layer constitute this particular problem, we introduce the advanced Slow Learner with Classifier Alignment (SLCA++) framework to unleash the power of Seq FT, serving as a strong baseline approach for CLPT. Our approach involves a Slow Learner to selectively reduce the learning rate of backbone parameters, and a Classifier Alignment to align the disjoint classification layers in a post-hoc fashion. We further enhance the efficacy of SL with a symmetric cross-entropy loss, as well as employ a parameter-efficient strategy to implement Seq FT with SLCA++. Across a variety of continual learning scenarios on image classification benchmarks, our approach provides substantial improvements and outperforms state-of-the-art methods by a large margin. Code: https://github.com/GengDavid/SLCA.