Calibrating CNNs for Few-Shot Meta Learning

Peng Yang, Shaogang Ren, Yang Zhao, Ping Li; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 2090-2099


Although few-shot meta learning has been extensively studied in machine learning community, the fast adaptation towards new tasks remains a challenge in the few-shot learning scenario. The neuroscience research reveals that the capability of evolving neural network formulation is essential for task adaptation, which has been broadly studied in recent meta-learning researches. In this paper, we present a novel forward-backward meta-learning framework (FBM) to facilitate the model generalization in few-shot learning from a new perspective, i.e., neuron calibration. In particular, FBM models the neurons in deep neural network-based model as calibrated units under a general formulation, where neuron calibration could empower fast adaptation capability to the neural network-based models through influencing both their forward inference path and backward propagation path. The proposed calibration scheme is lightweight and applicable to various feed-forward neural network architectures. Extensive empirical experiments on the challenging few-shot learning benchmarks validate that our approach training with neuron calibration achieves a promising performance, which demonstrates that neuron calibration plays a vital role in improving the few-shot learning performance.

Related Material

@InProceedings{Yang_2022_WACV, author = {Yang, Peng and Ren, Shaogang and Zhao, Yang and Li, Ping}, title = {Calibrating CNNs for Few-Shot Meta Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {2090-2099} }