AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning With Hyperspherical Embeddings

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

CVPR 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Alignment-based few-shot metric learning · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace EASE with noHubSIAMESE with ResNet-18 features · mini-ImageNet 1-shotaccuracy: 71.79 -> 73.18Improved
replace EASE with noHub-SSIAMESE with ResNet-18 features · tiered-ImageNet 1-shotaccuracy: 80.2 -> 81.34Improved
replace EASE with noHub-SSIAMESE with ResNet-18 features · CUB-200 1-shotaccuracy: 81.88 -> 83.92Improved
replace noHub with noHub-SSIAMESE with ResNet-18 features · mini-ImageNet 5-shotaccuracy: 82.58 -> 82.61No clear effect
replace noHub with noHub-SSIAMESE with ResNet-18 features · CUB-200 5-shotaccuracy: 89.13 -> 88.93Hurt
add label guidance to L_align only (ablation)noHub, tiered-ImageNet with ResNet-18 · 1-shotaccuracy: SimpleShot: 76.72 -> 78.25; 5-shot: 86.31 -> 85.46; SIAMESE: 82.94 -> 82.56; 5-shot: 87.87 -> 88.07Mixed
add label guidance to L_unif only (ablation)noHub, tiered-ImageNet with ResNet-18 · 1-shotaccuracy: SimpleShot: 76.72 -> 78.33; 5-shot: 86.31 -> 86.15; SIAMESE: 82.94 -> 82.81; 5-shot: 87.87 -> 88.43Mixed
add label guidance to both L_align and L_unif (ablation)noHub, tiered-ImageNet with ResNet-18 · 1-shotaccuracy: SimpleShot: 76.72 -> 78.35; SIAMESE: 82.94 -> 83.09Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy