AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Variational Few-Shot Learning

Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang

ICCV 2019 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Variational Bayesian deep learning · 160 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 aggregation of distributions instead of averaging embeddings (ablation)Variational few-shot · miniImagenet 5-way 5-shotaccuracy (%): 65.62 -> 71.54Improved
add aggregation of distributions instead of averaging embeddings (ablation)Variational few-shot · miniImagenet 5-way 1-shotaccuracy (%): 54.89 -> 57.15Improved
add the learnable-scalar transform function on variance (ablation)Variational few-shot · miniImagenet 5-way 1-shotaccuracy (%): 53.18 -> 57.15Improved
add the learnable-scalar transform function on variance (ablation)Variational few-shot · miniImagenet 5-way 5-shotaccuracy (%): 68.56 -> 71.54Improved
add two-stage (multi-stage) training with pre-trained features (ablation)Variational few-shot · miniImagenet 5-way 1-shotaccuracy (%): 55.17 -> 57.15Improved
add two-stage (multi-stage) training with pre-trained features (ablation)Variational few-shot · miniImagenet 5-way 5-shotaccuracy (%): 69.13 -> 71.54Improved
increase target size during training (ablation)Variational few-shot · miniImagenet 5-wayaccuracy (%)Improved
keep training support size equal to test support size (ablation)Variational few-shot · miniImagenet 5-wayaccuracy (%)Improved
swap ConvNet backbone for ResNet-12Variational few-shot · miniImagenet 5-way 1-shotaccuracy (%): 57.15 -> 61.23Improved
swap ConvNet backbone for ResNet-12Variational few-shot · miniImagenet 5-way 5-shotaccuracy (%): 71.54 -> 77.69Improved
add variational distribution learning to MaskNetMaskNet · Cluttered Omniglot segmentation (4 characters)IoU (%): 95.8 -> 97.9Improved
add variational distribution learning to MaskNetMaskNet · Cluttered Omniglot segmentation (256 characters)IoU (%): 43.7 -> 43.2Hurt

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