SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09352 · CVPR · 2023

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings

Rwiddhi Chakraborty, Michael Kampffmeyer, Sigurd Løkse, Robert Jenssen, Daniel Trosten, Knutsen Kristoffer, Wickstrøm

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the highdimensionality 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 1 . * Equal contributions. † UiT Machine Learning group (machine-learning.uit.no) and Visual Intelligence Centre (visual-intelligence.no).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.09352")
get_code_for_paper("2303.09352")
have("2303.09352")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.09352.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.09352.svg)](https://syntology.ai/paper/2303.09352)

Connect an agent — have() is free.