Continual Learning

Efficient Feature Transformations for Discriminative and Generative Continual Learning CVPR 2021 Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning NeurIPS 2021 Formalizing the Generalization-Forgetting Trade-off in Continual Learning NeurIPS 2021 Gradient Regularized Contrastive Learning for Continual Domain Adaptation AAAI 2021 Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation CVPR 2021 I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting AAAI 2021 IIRC: Incremental Implicitly-Refined Classification CVPR 2021 Incremental Embedding Learning via Zero-Shot Translation AAAI 2021 Incremental Learning via Rate Reduction CVPR 2021 KSM: Fast Multiple Task Adaption via Kernel-Wise Soft Mask Learning CVPR 2021 Layerwise Optimization by Gradient Decomposition for Continual Learning CVPR 2021 Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning EMNLP 2021 Learning the Superpixel in a Non-Iterative and Lifelong Manner CVPR 2021 Mitigating Forgetting in Online Continual Learning with Neuron Calibration NeurIPS 2021 Multi-Domain Multi-Task Rehearsal for Lifelong Learning AAAI 2021 Optimizing Reusable Knowledge for Continual Learning via Metalearning NeurIPS 2021 ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-Supervised Continual Learning CVPR 2021 Overcoming Catastrophic Forgetting in Graph Neural Networks AAAI 2021 Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay AAAI 2021 PLOP: Learning Without Forgetting for Continual Semantic Segmentation CVPR 2021 Posterior Meta-Replay for Continual Learning NeurIPS 2021 Prototype Augmentation and Self-Supervision for Incremental Learning CVPR 2021 Rainbow Memory: Continual Learning With a Memory of Diverse Samples CVPR 2021 Rational LAMOL: A Rationale-based Lifelong Learning Framework ACL 2021 Remember More by Recalling Less: Investigating the Role of Batch Size in Continual Learning with Experience Replay (Student Abstract) AAAI 2021