AI Paper Atlas

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

Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning

Milad Abdollahzadeh, Touba Malekzadeh, Ngai-man Cheung

NeurIPS 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-augmentation and meta-objectives · 3 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 KML modulation to MMAMLMMAML · Multimodal 2Mode 5-shotaccuracy: 73.52 -> 77.02Improved
add KML modulation to MProtoNetMProtoNet · Multimodal 5Mode 5-shotaccuracy: 59.95 -> 64.91Improved
add KML modulation to MMAMLMMAML · Multimodal 2Mode-dagger 5-shotaccuracy: 52.02 -> 53.72Improved
replace MAML with ProtoNet as meta-learner in MMAMLMMAML · Multimodal 2Mode-dagger 1-shotaccuracy: 39.11 -> 43.57Improved
train one multimodal ProtoNet instead of separate shared modelMulti-ProtoNet vs ProtoNet · Multimodal 2Mode-dagger 5-shotaccuracy: 57.70 -> 56.73Hurt
modulate all layers (no shared layers) in multimodal setting (ablation)MProtoNet+KML · Multimodal 2Mode-dagger 1-shotaccuracy: 43.05 -> 44.40Improved
share first layer in multimodal setting (ablation)MProtoNet+KML · Multimodal 2Mode-dagger 1-shotaccuracy: 44.40 -> 44.18Hurt
share first two layers in unimodal KML (ablation)KML-ProtoNet · mini-ImageNet 1-shotaccuracy: 51.55 -> 54.10Improved
share first, second and third layers in unimodal KML (ablation)KML-ProtoNet · mini-ImageNet 1-shotaccuracy: 54.10 -> 52.83Hurt
share only the first layer in unimodal KML (ablation)KML-ProtoNet · mini-ImageNet 5-shotaccuracy: 67.18 -> 68.07Improved
unimodal KML with two shared layers (ablation)KML-ProtoNet · tiered-ImageNet 1-shotaccuracy: 53.01 -> 54.67Improved
add KML to MMAML for RLMMAML · Point Mass 2D 2 modescumulative reward: -136 -> -121Improved

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