AAAI 2024 accepted papers on Continual learning
49 of the 2,864 papers accepted at AAAI 2024 (1.7%) are on Continual learning, compared with 1.5% at AAAI 2023. They fall into 4 topics.
See AAAI 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Online and replay-based · 23 papers
- Towards Continual Knowledge Graph Embedding via Incremental Distillation (42 citations)
- What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection (30 citations)
- Efficient Spiking Neural Networks with Sparse Selective Activation for Continual Learning (28 citations)
- Influential Exemplar Replay for Incremental Learning in Recommender Systems (23 citations)
- Pre-trained Online Contrastive Learning for Insurance Fraud Detection (22 citations)
- Continual Relation Extraction via Sequential Multi-Task Learning (16 citations)
- Summarizing Stream Data for Memory-Constrained Online Continual Learning (16 citations)
- Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation (14 citations)
- Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning (14 citations)
- Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning (12 citations)
- Live and Learn: Continual Action Clustering with Incremental Views (10 citations)
- Task-Free Continual Generation and Representation Learning via Dynamic Expansionable Memory Cluster (10 citations)
and 11 more in the interactive map.
Class-incremental · 13 papers
- DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning (38 citations)
- eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation (21 citations)
- Fine-Grained Knowledge Selection and Restoration for Non-exemplar Class Incremental Learning (17 citations)
- M2SD:Multiple Mixing Self-Distillation for Few-Shot Class-Incremental Learning (14 citations)
- Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection (12 citations)
- Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement (11 citations)
- Cross-Class Feature Augmentation for Class Incremental Learning (9 citations)
- Adaptive Discovering and Merging for Incremental Novel Class Discovery (8 citations)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (6 citations)
- TIKP: Text-to-Image Knowledge Preservation for Continual Semantic Segmentation (6 citations)
- Defying Imbalanced Forgetting in Class Incremental Learning (4 citations)
- Hypercorrelation Evolution for Video Class-Incremental Learning (4 citations)
and 1 more in the interactive map.
Domain and prompt-based · 11 papers
- Unsupervised Continual Anomaly Detection with Contrastively-Learned Prompt (39 citations)
- Multi-Domain Incremental Learning for Face Presentation Attack Detection (30 citations)
- LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-identification (26 citations)
- Non-exemplar Domain Incremental Object Detection via Learning Domain Bias (19 citations)
- Evolving Parameterized Prompt Memory for Continual Learning (18 citations)
- MIND: Multi-Task Incremental Network Distillation (18 citations)
- Learning to Prompt Knowledge Transfer for Open-World Continual Learning (16 citations)
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention (12 citations)
- HOP to the Next Tasks and Domains for Continual Learning in NLP (6 citations)
- Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing (4 citations)
- SimCS: Simulation for Domain Incremental Online Continual Segmentation (3 citations)