"Matching Feature Sets for Few-Shot Image Classification": IID researchers on the CVPR 2022 program

The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) is the most important annual event in the field of computer vision. A paper produced by IID students and researchers is on the program of the event, “Matching Feature Sets for Few-Shot Image Classification” by Arman Afrasiyabi, Jean-François Lalonde, Christian Gagné, and Hugo Larochelle from Google Brain. 

Abstract :

In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classification methods also mostly follow this trend.

In this work, we depart from this established direction and instead propose to extract sets of feature vectors for each image. We argue that a set-based representation intrinsically builds a richer representation of images from the base classes, which can subsequently better transfer to the few-shot classes. To do so, we propose to adapt existing feature extractors to instead produce sets of feature vectors from images. Our approach, dubbed SetFeat, embeds shallow self-attention mechanisms inside existing encoder architectures. The attention modules are lightweight, and as such our method results in encoders that have approximately the same number of parameters as their original versions. During training and inference, a set-to-set matching metric is used to perform image classification.

The effectiveness of our proposed architecture and metrics is demonstrated via thorough experiments on standard few-shot datasets — namely miniImageNet, tieredImageNet, and CUB — in both the 1- and 5-shot scenarios. In all cases but one, our method outperforms the state-of-the-art.

About CVPR 2022:

Presented June 19-23 live from New Orleans, USA, the IEEE / CVF Conference on Computer Vision and Pattern Recognition (CVPR) is the premier annual event in the field of computer vision, which includes the main conference and several workshops and short courses. With its high quality and low cost, it offers exceptional value to students, academics, and industry researchers.

CVPR 2022 will be a hybrid conference, with both in-person and virtual participation options. Conference content hosted on the virtual platform will be available exclusively to registered CVPR participants. Conference proceedings will be publicly available via the CVPR website, and the final version will be published on IEEE Xplore after the conference.

Discover the event’s full program

Let’s keep in touch!

Would you like to be informed about IID news and activities? Subscribe now to our monthly newsletter.