XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning

Abstract

Learning novel concepts while preserving prior knowledge is a long-standing challenge in machine learning. The challenge gets greater when a novel task is given with only a few labeled examples, a problem known as incremental few-shot learning. We propose XtarNet, which learns to extract task-adaptive representation (TAR) for facilitating incremental few-shot learning. The method utilizes a backbone network pretrained on a set of base categories while also employing additional modules that are meta-trained across episodes. Given a new task, the novel feature extracted from the meta-trained modules is mixed with the base feature obtained from the pretrained model. The process of combining two different features provides TAR and is also controlled by meta-trained modules. The TAR contains effective information for classifying both novel and base categories. The base and novel classifiers quickly adapt to a given task by utilizing the TAR. Experiments on standard image datasets indicate that XtarNet achieves state-of-the-art incremental few-shot learning performance. The concept of TAR can also be used in conjunction with existing incremental few-shot learning methods; extensive simulation results in fact show that applying TAR enhances the known methods significantly.

In Proceedings of the 37th International Conference on Machine Learning (ICML) 2020, Vienna, Austria, PMLR 119; *Equal contribution

References in corpus (8)

• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• FearNet: Brain-Inspired Model for Incremental Learning
• Continual Learning with Deep Generative Replay
• TADAM: Task dependent adaptive metric for improved few-shot learning
• Cross Attention Network for Few-shot Classification
• TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

Cited by in corpus (2)

• A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
• Dataset Bias in Few-shot Image Recognition