A Closer Look at Few-shot Classification Again
This work provides incremental insights for researchers in few-shot learning by clarifying phase interactions and offering new research challenges.
The authors tackled the problem of few-shot classification by empirically demonstrating that training and adaptation phases can be disentangled, enabling independent analysis and design for each phase, with insights connecting to visual representation learning and transfer learning.
Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper, we empirically prove that the training algorithm and the adaptation algorithm can be completely disentangled, which allows algorithm analysis and design to be done individually for each phase. Our meta-analysis for each phase reveals several interesting insights that may help better understand key aspects of few-shot classification and connections with other fields such as visual representation learning and transfer learning. We hope the insights and research challenges revealed in this paper can inspire future work in related directions. Code and pre-trained models (in PyTorch) are available at https://github.com/Frankluox/CloserLookAgainFewShot.