# Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning

arXiv: https://arxiv.org/abs/2508.01579 · HTML: https://mlsanity.com/paper/2508.01579/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 3 Aug 2025.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [RanPAC: Random Projections and Pre-trained Models for Continual Learning](https://mlsanity.com/paper/2307.02251/) (2023)
- [Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation](https://mlsanity.com/paper/2204.00895/) (2022)
- [Continual Learning with Node-Importance based Adaptive Group Sparse Regularization](https://mlsanity.com/paper/2003.13726/) (2020)
- [Consistent Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2403.08568/) (2024)
- [Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion](https://mlsanity.com/paper/2407.14143/) (2024)
- [On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning](https://mlsanity.com/paper/2210.06443/) (2022)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [Visual Prompt Tuning in Null Space for Continual Learning](https://mlsanity.com/paper/2406.05658/) (2024)
- [Semantic Residual Prompts for Continual Learning](https://mlsanity.com/paper/2403.06870/) (2024)
- [CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning](https://mlsanity.com/paper/2507.09471/) (2025)

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

- [Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting](https://mlsanity.com/paper/2508.04227/) (2025)
- [Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning](https://mlsanity.com/paper/2603.00191/) (2026)
- [Reasoning-Driven Multimodal LLM for Domain Generalization](https://mlsanity.com/paper/2602.23777/) (2026)
- [Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement](https://mlsanity.com/paper/2606.24161/) (2026)
- [Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection](https://mlsanity.com/paper/2607.13452/) (2026)
- [DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP](https://mlsanity.com/paper/2509.23335/) (2025)
- [PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization](https://mlsanity.com/paper/2609.04837/) (2026)
- [CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization](https://mlsanity.com/paper/2609.10158/) (2026)
- [Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning](https://mlsanity.com/paper/2609.36759/) (2026)
- [Generalized Biomedicine Discovery](https://mlsanity.com/paper/2610.00120/) (2026)

## Abstract (arXiv)

Continual learning (CL) aims to equip models with the ability to learn from a stream of tasks without forgetting previous knowledge. With the progress of vision-language models like Contrastive Language-Image Pre-training (CLIP), their promise for CL has attracted increasing attention due to their strong generalizability. However, the potential of rich textual semantic priors in CLIP in addressing the stability-plasticity dilemma remains underexplored. During backbone training, most approaches transfer past knowledge without considering semantic relevance, leading to interference from unrelated tasks that disrupt the balance between stability and plasticity. Besides, while text-based classifiers provide strong generalization, they suffer from limited plasticity due to the inherent modality gap in CLIP. Visual classifiers help bridge this gap, but their prototypes lack rich and precise semantics. To address these challenges, we propose Semantic-Enriched Continual Adaptation (SECA), a unified framework that harnesses the anti-forgetting and structured nature of textual priors to guide semantic-aware knowledge transfer in the backbone and reinforce the semantic structure of the visual classifier. Specifically, a Semantic-Guided Adaptive Knowledge Transfer (SG-AKT) module is proposed to assess new images' relevance to diverse historical visual knowledge via textual cues, and aggregate relevant knowledge in an instance-adaptive manner as distillation signals. Moreover, a Semantic-Enhanced Visual Prototype Refinement (SE-VPR) module is introduced to refine visual prototypes using inter-class semantic relations captured in class-wise textual embeddings. Extensive experiments on multiple benchmarks validate the effectiveness of our approach.