CVPR 2023 accepted papers on Continual learning
44 of the 2,359 papers accepted at CVPR 2023 (1.9%) are on Continual learning, compared with 1.8% at CVPR 2022. They fall into 4 topics.
See CVPR 2023 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
Class-incremental · 21 papers
- Learning With Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning (113 citations)
- Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation (106 citations)
- Continual Detection Transformer for Incremental Object Detection (93 citations)
- PCR: Proxy-Based Contrastive Replay for Online Class-Incremental Continual Learning (75 citations)
- Class-Incremental Exemplar Compression for Class-Incremental Learning (71 citations)
- GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task (70 citations)
- Dense Network Expansion for Class Incremental Learning (68 citations)
- On the Stability-Plasticity Dilemma of Class-Incremental Learning (65 citations)
- Federated Incremental Semantic Segmentation (58 citations)
- Endpoints Weight Fusion for Class Incremental Semantic Segmentation (51 citations)
- Continual Semantic Segmentation With Automatic Memory Sample Selection (44 citations)
- Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class (41 citations)
and 9 more in the interactive map.
Online and replay-based · 16 papers
- GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting (51 citations)
- AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning (48 citations)
- Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning (42 citations)
- Computationally Budgeted Continual Learning: What Does Matter? (38 citations)
- VQACL: A Novel Visual Question Answering Continual Learning Setting (36 citations)
- Real-Time Evaluation in Online Continual Learning: A New Hope (35 citations)
- Regularizing Second-Order Influences for Continual Learning (24 citations)
- Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling (24 citations)
- Adaptive Plasticity Improvement for Continual Learning (19 citations)
- Bilateral Memory Consolidation for Continual Learning (17 citations)
- Decoupling Learning and Remembering: A Bilevel Memory Framework With Knowledge Projection for Task-Incremental Learning (14 citations)
- Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning (12 citations)
and 4 more in the interactive map.
Domain and prompt-based · 5 papers
- CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning (320 citations)
- EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization (65 citations)
- PIVOT: Prompting for Video Continual Learning (46 citations)
- Unsupervised Continual Semantic Adaptation Through Neural Rendering (18 citations)
- Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions (15 citations)