ECCV 2024 accepted papers on Continual learning
47 of the 2,387 papers accepted at ECCV 2024 (2.0%) are on Continual learning, compared with 1.6% at ECCV 2022. They fall into 4 topics.
See ECCV 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Class-incremental · 25 papers
- An Incremental Unified Framework for Small Defect Inspection (28 citations)
- Few-shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt (28 citations)
- PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning (28 citations)
- DiffClass: Diffusion-Based Class Incremental Learning (27 citations)
- MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment (22 citations)
- Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation (18 citations)
- CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning (17 citations)
- Mitigating Background Shift in Class-Incremental Semantic Segmentation (17 citations)
- Exemplar-free Continual Representation Learning via Learnable Drift Compensation (15 citations)
- Rethinking Few-shot Class-incremental Learning: Learning from Yourself (14 citations)
- Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentation (13 citations)
- RCS-Prompt: Learning Prompt to Rearrange Class Space for Prompt-based Continual Learning (10 citations)
and 13 more in the interactive map.
Online and replay-based · 13 papers
- Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning (32 citations)
- Weighted Ensemble Models Are Strong Continual Learners (27 citations)
- Learning to Unlearn for Robust Machine Unlearning (25 citations)
- PromptFusion: Decoupling Stability and Plasticity for Continual Learning (23 citations)
- One-stage Prompt-based Continual Learning (16 citations)
- PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery (12 citations)
- Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference (6 citations)
- Anytime Continual Learning for Open Vocabulary Classification (5 citations)
- Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM (5 citations)
- Pick-a-back: Selective Device-to-Device Knowledge Transfer in Federated Continual Learning (5 citations)
- Open-World Dynamic Prompt and Continual Visual Representation Learning (4 citations)
- CLEO: Continual Learning of Evolving Ontologies (2 citations)
and 1 more in the interactive map.
Continual fine-tuning of LLMs · 5 papers
- MagMax: Leveraging Model Merging for Seamless Continual Learning (37 citations)
- Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion (33 citations)
- Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning (27 citations)
- Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models (26 citations)
- Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models (11 citations)
Domain and prompt-based · 4 papers
- Non-Exemplar Domain Incremental Learning via Cross-Domain Concept Integration (13 citations)
- Semantic Residual Prompts for Continual Learning (10 citations)
- Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation (9 citations)
- Human Motion Forecasting in Dynamic Domain Shifts: A Homeostatic Continual Test-time Adaptation Framework
