ECCV 2022 accepted papers on Continual learning
27 of the 1,645 papers accepted at ECCV 2022 (1.6%) are on Continual learning, compared with 0.8% at ECCV 2020. They fall into 3 topics.
See ECCV 2022 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 · 14 papers
- FOSTER: Feature Boosting and Compression for Class-Incremental Learning (403 citations)
- Few-Shot Class-Incremental Learning from an Open-Set Perspective (120 citations)
- Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay (118 citations)
- R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning (88 citations)
- Class-Incremental Novel Class Discovery (54 citations)
- Long-Tailed Class Incremental Learning (49 citations)
- S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning (48 citations)
- Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer (41 citations)
- Novel Class Discovery without Forgetting (41 citations)
- RBC: Rectifying the Biased Context in Continual Semantic Segmentation (34 citations)
- Continual Semantic Segmentation via Structure Preserving and Projected Feature Alignment (24 citations)
- incDFM: Incremental Deep Feature Modeling for Continual Novelty Detection (13 citations)
and 2 more in the interactive map.
Online and replay-based · 9 papers
- Transfer without Forgetting (49 citations)
- CoSCL: Cooperation of Small Continual Learners Is Stronger than a Big One (43 citations)
- Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (38 citations)
- Helpful or Harmful: Inter-Task Association in Continual Learning (28 citations)
- Anti-Retroactive Interference for Lifelong Learning (26 citations)
- Continual Variational Autoencoder Learning via Online Cooperative Memorization (20 citations)
- Online Task-Free Continual Learning with Dynamic Sparse Distributed Memory (20 citations)
- Theoretical Understanding of the Information Flow on Continual Learning Performance (5 citations)
- Online Continual Learning with Contrastive Vision Transformer
Continual fine-tuning of LLMs · 4 papers
- DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning (616 citations)
- Learning with Recoverable Forgetting (32 citations)
- Incremental Task Learning with Incremental Rank Updates (17 citations)
- DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning (16 citations)
