AI Paper Atlas

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

A Multi-Mode Modulator for Multi-Domain Few-Shot Classification

Yanbin Liu, Juho Lee, Linchao Zhu, Ling Chen, Humphrey Shi, Yi Yang

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 30 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 domain-cooperative set to domain-specific set (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 71.9 -> 73.9Improved
add domain-specific set to domain-cooperative set (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 73.0 -> 73.9Improved
use cooperative instead of specific parameters on Omniglot (ablation)tri-M · Omniglotaccuracy: 88.2 -> 90.5Improved
use cooperative instead of specific parameters on QuickDraw (ablation)tri-M · QuickDrawaccuracy: 75.1 -> 76.2Improved
use 8 modes instead of 4 domain-specific and 4 cooperative modes (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 72.7 -> 73.9Improved
increase cooperative modes from 8 to 16 (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 73.9 -> 73.0Hurt
increase both mode counts from 8 to 16 (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 73.9 -> 72.2Hurt
add modulation on shallowest layer group (3 to 4 groups) (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 71.7 -> 73.9Improved
modulate 4 layer groups instead of 1 (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 68.3 -> 73.9Improved
modulate all layers instead of only second conv of each block (ablation)tri-M · Meta-Dataset (13 datasets)accuracy: 73.1 -> 73.9No clear effect
tri-M versus SimpleCNAPS on unseen domainstri-M · Meta-Dataset out-of-domainaccuracy: 69.7 -> 72.9Improved

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