Awesome Few-Shot Class-Incremental Learning

Papers

2022

  • Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks(TPAMI22)[paper][Code]

  • Forward Compatible Few-Shot Class-Incremental Learning(CVPR22) [paper] [Code]

  • MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning (CVPR22) [paper]

  • Constrained Few-shot Class-incremental Learning (CVPR22) [paper]

  • Subspace Regularizers for Few-Shot Class Incremental Learning (ICLR22) [paper]

  • Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay (ECCV22) [paper]

    2021

  • Learning adaptive classifiers synthesis for generalized few-shot learning(IJCV21) [paper] [Code]

  • MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning(TPAMI21) [paper]

  • Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting(ICCV21) [paper]

  • Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces(ICCV21) [paper]

  • GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning(ICML21) [paper]

  • Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima(NeurIPS21) [paper]

  • Few-shot incremental learning with continually evolved classifiers(CVPR21) [paper]

  • Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning(CVPR21) [paper]

  • Semantic-Aware Knowledge Distillation for Few-Shot Class-Incremental Learning (CVPR21) [paper]

  • Incremental few-shot learning via vector quantization in deep embedded space(ICLR21) [paper]

  • Few-Shot Lifelong Learning(AAAI21) [paper]

2020

  • Few-Shot Class-Incremental Learning (CVPR20) [paper]
  • Incremental Few-Shot Object Detection(CVPR20) [paper]
  • XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning(ICML20) [paper]

2019

  • Incremental few-shot learning with attention attractor networks(NeurIPS19) [paper]

2018

  • Dynamic few-shot visual learning without forgetting(CVPR18) [paper]

Feel free to contact me if you find any interesting paper is missing.