🚀Feel free to contact me or add pull request if you find👀 any interesting paper is missing.
📋Markdown format:
- Paper Name. (**Conference Year**) [[paper](link)] [[code](link)]- Continual Learning with Pre-Trained Models: A Survey (arXiv23)[paper] [code]
- Deep Class-Incremental Learning: A Survey (arXiv23)[paper] [code]
- Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need (arXiv23)[paper] [code]
- PromptFusion: Decoupling Stability and Plasticity for Continual Learning (arXiv23)[paper]
- CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning (CVPR23)[paper] [code]
- Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference (AAAI23)[paper] [code]
- PIVOT: Prompting for Video Continual Learning (CVPR23)[paper]
- DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning (ICML23)[paper]
- Learning Expressive Prompting With Residuals for Vision Transformers (CVPR23)[paper]
- Multimodal Parameter-Efficient Few-Shot Class Incremental Learning (arXiv23)[paper]
- Real-Time Evaluation in Online Continual Learning: A New Hope (CVPR23 Highlight)[paper] [code]
- Remind of the Past: Incremental Learning with Analogical Prompts (arXiv23)[paper] [code]
- On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code (arXiv23)[paper]
- AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning (CVPR23)[paper]
- Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class (CVPR23)[paper]
- Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation (CVPR23)[paper]
- Continual Detection Transformer for Incremental Object Detection (CVPR23)[paper] [code]
- Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions (CVPR23)[paper]
- Computationally Budgeted Continual Learning: What Does Matter? (CVPR23)[paper] [code]
- Unsupervised Continual Semantic Adaptation through Neural Rendering (CVPR23)[paper]
- ConStruct-VL: Data-Free Continual Structured VL Concepts Learning (CVPR23)[paper] [code]
- Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning (CVPR23)[paper] [code]
- Learning without Forgetting for Vision-Language Models (arXiv23)[paper]
- Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learning (arXiv23)[paper]
- Introducing Language Guidance in Prompt-based Continual Learning (ICCV23)[paper]
- When Prompt-based Incremental Learning Does Not Meet Strong Pretraining (ICCV23)[paper] [code]
- Class Incremental Learning with Pre-trained Vision-Language Models (arXiv23)[paper]
- Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (NeurIPS23)[paper] [code]
- FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning (NeurIPS23)[paper] [code]
- RanPAC: Random Projections and Pre-trained Models for Continual Learning (NeurIPS23)[paper] [code]
- Continual Learners are Incremental Model Generalizers (ICML23)[paper]
- DDGR: Continual Learning with Deep Diffusion-based Generative Replay (ICML23)[paper] [code]
- Continual Vision-Language Representation Learning with Off-Diagonal Information (ICML23)[paper]
- Self-regulating Prompts: Foundational Model Adaptation without Forgetting (ICCV23)[paper] [code]
- CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation (ICCV23)[paper] [code]
- Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning (ICCV23)[paper] [code]
- First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning (ICCV23)[paper]
- Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models (ICCV23)[paper] [code]
- A Unified Continual Learning Framework with General Parameter-Efficient Tuning (ICCV23)[paper] [code]
- SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model (ICCV23)[paper] [code]
- Class-Incremental Learning with Strong Pre-trained Models (CVPR22)[paper] [code]
- Learning to Prompt for Continual Learning (CVPR22)[paper] [code]
- S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning (NeurIPS22)[paper] [code]
- Don't Stop Learning: Towards Continual Learning for the CLIP Model (arXiv22)[paper]
- DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning (ECCV22)[paper] [code]
- Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection (COLING22)[paper]
- Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning (NeurIPS22)[paper]
- Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue (ENNLP22)[paper]
- CLIP model is an Efficient Continual Learner (arXiv22)[paper] [code]
- Memory Efficient Continual Learning with Transformers (NeurIPS22)[paper]
- Continual Pre-Training Mitigates Forgetting in Language and Vision (arXiv22)[paper] [code]
- Fine-tuned Language Models are Continual Learners (arXiv22)[paper] [code]
- Continual Learning with Foundation Models: An Empirical Study of Latent Replay (CoLLAs22)[paper] [code]
- Effect of scale on catastrophic forgetting in neural networks (ICLR22)[paper]
- Continual Training of Language Models for Few-Shot Learning (arXiv22)[paper] [code]
- CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks (NeurIPS22)[paper] [code]
- A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning (arXiv22)[paper] [code]
- ELLE: Efficient Lifelong Pre-training for Emerging Data (ACL22)[paper] [code]