AI Paper Atlas

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

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation

Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim

NeurIPS 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-augmentation and meta-objectives · 70 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
Condition MAML initialization on task-mode information using modulationMAML · Multimodal few-shot image classification, 2-mode 5-way 1-shotaccuracy: 66.80% -> 69.93%Improved
Condition MAML initialization on task-mode information using modulationMAML · Multimodal few-shot image classification, 3-mode 5-way 5-shotaccuracy: 67.97% -> 70.15%Improved
Condition MAML initialization on task-mode information using modulationMAML · Multimodal few-shot image classification, 5-mode 5-way 5-shotaccuracy: 54.41% -> 60.83%Improved
Use MMAML instead of MAMLMAML · Multimodal few-shot image classification, 2-mode 20-way 1-shotaccuracy: 44.69% -> 47.80%Improved
Use MMAML instead of Multi-MAML with ground-truth mode labelsMulti-MAML · Multimodal few-shot image classification, 5-mode 5-way 5-shotaccuracy: 55.92% -> 60.83%Improved
Use MMAML instead of MAMLMAML · Multimodal few-shot image classification, 3-mode 20-way 1-shotaccuracy: 28.22% -> 36.27%Improved
Use MMAML instead of MAMLMAML · Multimodal few-shot image classification, 5-mode 20-way 1-shotaccuracy: 28.85% -> 33.97%Improved
Use MMAML instead of Multi-MAML with ground-truth mode labelsMulti-MAML · Multimodal few-shot image classification, 2-mode 20-way 1-shotaccuracy: 53.15% -> 47.80%Hurt
Use MMAML instead of Multi-MAML with ground-truth mode labelsMulti-MAML · Multimodal few-shot image classification, 3-mode 20-way 1-shotaccuracy: 39.77% -> 36.27%Hurt
Add task-aware modulation to ProMPProMP · Point Mass 2D, 2 modescumulative reward per episode: -397 $\pm$ 20 -> -136 $\pm$ 8Improved
Add task-aware modulation to ProMPProMP · Point Mass 2D, 4 modescumulative reward per episode: -523 $\pm$ 51 -> -209 $\pm$ 32Improved
Add task-aware modulation to ProMPProMP · Reacher, 4 modescumulative reward per episode: -13.8 $\pm$ 2.5 -> -11.0 $\pm$ 0.8Improved

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