Gestalt-Guided Image Understanding for Few-Shot Learning

Kun Song, Yuchen Wu, Jiansheng Chen, Tianyu Hu, Huimin Ma; Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 824-840


Due to the scarcity of available data, deep learning does not perform well on few-shot learning tasks. However, human can quickly learn the feature of a new category from very few samples. Nevertheless, previous work has rarely considered how to mimic human cognitive behavior and apply it to few-shot learning. This paper introduces Gestalt psychology to few-shot learning and proposes Gestalt-Guided Image Understanding, a plug-and-play method called GGIU. Referring to the principle of totality and the law of closure in Gestalt psychology, we design Totality-Guided Image Understanding and Closure-Guided Image Understanding to extract image features. After that, a feature estimation module is used to estimate the accurate features of images. Extensive experiments demonstrate that our method can improve the performance of existing models effectively and flexibly without retraining or fine-tuning.

Related Material

[pdf] [arXiv] [code]
@InProceedings{Song_2022_ACCV, author = {Song, Kun and Wu, Yuchen and Chen, Jiansheng and Hu, Tianyu and Ma, Huimin}, title = {Gestalt-Guided Image Understanding for Few-Shot Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {824-840} }