AI Paper Atlas

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

Associative Alignment for Few-shot Image Classification

Arman Afrasiyabi, Jean-François Lalonde, Christian Gagné

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 168 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
add centroid associative alignment of related base classesarcmax baseline, ResNet-18 · mini-ImageNet 5-shotaccuracy: 76.62 -> 80.35Improved
add adversarial associative alignment of related base classesarcmax baseline, ResNet-18 · mini-ImageNet 5-shotaccuracy: 76.62 -> 77.92Improved
add centroid associative alignmentarcmax baseline, Conv4 · mini-ImageNet 5-shotaccuracy: 69.07 -> 71.45Improved
use adversarial instead of centroid alignmentalignment, Conv4 · CUB 1-shotaccuracy: 62.71 -> 63.30Improved
add adversarial alignment in cross-domain transferarcmax baseline, ResNet-18 · mini-ImageNet to CUB 1-shotaccuracy: 45.60 -> 44.37Hurt
add centroid alignment in cross-domain transferarcmax baseline, ResNet-18 · mini-ImageNet to CUB 5-shotaccuracy: 64.93 -> 70.37Improved
add alignment loss (centroid) to training on novel plus related base classes (ablation)related-base fine-tuning, ResNet-18 · mini-ImageNet 1-shotaccuracy: 55.94 -> 59.88Improved
train on related base classes without alignment loss (ablation)arcmax baseline, Conv4 · mini-ImageNet 1-shotaccuracy: 51.90 -> 52.72No clear effect
increase number of related base classes B from 1 to 10 (centroid) (ablation)centroid alignment, ResNet-18 · mini-ImageNet 5-shotaccuracy: 77.54 -> 80.23Improved
increase number of related base classes B from 1 to 10 (adversarial) (ablation)adversarial alignment, ResNet-18 · mini-ImageNet 5-shotaccuracy: 79.34 -> 77.92Hurt
use selected related base classes instead of random ones (ablation)centroid alignment, ResNet-18 · mini-ImageNet 5-shotaccuracy: 76.19 -> 80.35Improved
use arcmax with early stopping instead of cosmax (ablation)baseline, Conv4 · mini-ImageNet 5-shotaccuracy: 68.47 -> 69.07Improved

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