Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting

Skip the second phase In the proposed work, we address the problem of generalized few-shot learning with a three-phase framework. During the second phase we target to improve novel class learning and to mitigate catastrophic forgetting of the base classes. In Fig. 1 we show the development of the performance when we skip the second phase and directly proceed with the third phase. During the third, joint calibration phase, the training set consists of base (one sample per class) and all novel training samples. The performance of the base classes in the joint space BJ and the separate space BB stays at high level even with few training samples. While the separate novel NN performance can reach high values during the third phase, novel class learning in the joint space suffers from strong bias towards base classes (red curve on the figure stays low). It shows that our second phase for explicit novel learning in the joint space gives a significant boost to the overall performance in the joint space. skip 2 phase