AI Paper Atlas

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

Multi-modal Cycle-consistent Generalized Zero-Shot Learning

Rafael Felix, Vijay B. G. Kumar, Ian Reid, Gustavo Carneiro

ECCV 2018 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 396 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 multi-modal cycle-consistency loss (cycle-WGAN)f-CLSWGAN baseline · CUB GZSLharmonic mean H: 50.8 -> 52.2Improved
add multi-modal cycle-consistency loss (cycle-WGAN)f-CLSWGAN baseline · FLO GZSLharmonic mean H: 63.9 -> 64.5Improved
add multi-modal cycle-consistency loss (cycle-WGAN)f-CLSWGAN baseline · SUN GZSLharmonic mean H: 38.7 -> 39.2Improved
add multi-modal cycle-consistency loss (cycle-WGAN)f-CLSWGAN baseline · AWA GZSLharmonic mean H: 59.2 -> 59.7Improved
add cycle loss on top of classification loss (cycle-CLSWGAN)f-CLSWGAN baseline · SUN GZSLharmonic mean H: 38.7 -> 40.0Improved
also use synthetic features of unseen classes in cycle loss (cycle-(U)WGAN) instead of seen only (ablation)cycle-WGAN · CUB GZSLharmonic mean H: 52.2 -> 53.0Improved
also use synthetic features of unseen classes in cycle loss (cycle-(U)WGAN) instead of seen only (ablation)cycle-WGAN · SUN GZSLharmonic mean H: 39.2 -> 39.4 (unseen acc 48.3 -> 47.2)Mixed
also use synthetic features of unseen classes in cycle loss (cycle-(U)WGAN) instead of seen only (ablation)cycle-WGAN · AWA GZSLunseen accuracy: 56.4 -> 59.6Improved
add cycle-consistency loss with unseen-class synthesis (cycle-(U)WGAN)f-CLSWGAN baseline · FLO ZSLtop-1 accuracy: 66.8 -> 70.3Improved
add cycle-consistency loss with unseen-class synthesis (cycle-(U)WGAN)f-CLSWGAN baseline · CUB ZSLtop-1 accuracy: 57.7 -> 58.6Improved
add cycle-consistency loss with unseen-class synthesis (cycle-(U)WGAN)f-CLSWGAN baseline · AWA ZSLtop-1 accuracy: 64.1 -> 66.8Improved
add cycle-consistency loss with unseen-class synthesis (cycle-(U)WGAN)f-CLSWGAN baseline · SUN ZSLtop-1 accuracy: 58.5 -> 59.9Improved

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