Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning with Hyperspherical Embeddings
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Indsendt manuskript, 1,39 MB, PDF-dokument
Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are prone to suffer from the hubness problem, where a few points (hubs) occur frequently in multiple nearest neighbour lists of other points. Hubness negatively impacts distance-based classification when hubs from one class appear often among the nearest neighbors of points from another class, degrading the classifier's performance. To address the hubness problem in FSL, we first prove that hubness can be eliminated by distributing representations uniformly on the hypersphere. We then propose two new approaches to embed representations on the hypersphere, which we prove optimize a tradeoff between uniformity and local similarity preservation - reducing hubness while retaining class structure. Our experiments show that the proposed methods reduce hubness, and significantly improves transductive FSL accuracy for a wide range of classifiers 11Code available at https://github.com/uitml/noHub..
Originalsprog | Engelsk |
---|---|
Titel | Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 |
Antal sider | 10 |
Forlag | IEEE Computer Society Press |
Publikationsdato | 2023 |
Sider | 7527-7536 |
ISBN (Elektronisk) | 9798350301298 |
DOI | |
Status | Udgivet - 2023 |
Begivenhed | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada Varighed: 18 jun. 2023 → 22 jun. 2023 |
Konference
Konference | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 |
---|---|
Land | Canada |
By | Vancouver |
Periode | 18/06/2023 → 22/06/2023 |
Sponsor | Amazon Science, Ant Research, Cruise, et al., Google, Lambda |
Bibliografisk note
Funding Information:
This work was financially supported by the Research Council of Norway (RCN), through its Centre for Research-based Innovation funding scheme (Visual Intelligence, grant no. 309439), and Consortium Partners. It was further funded by RCN FRIPRO grant no. 315029, RCN IKTPLUSS grant no. 303514, and the UiT Thematic Initiative “Data-Driven Health Technology”.
Publisher Copyright:
© 2023 IEEE.
ID: 371288564