AI Paper Atlas

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

Towards Recognizing Unseen Categories in Unseen Domains

Massimiliano Mancini, Zeynep Akata, Elisa Ricci, Barbara Caputo

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 88 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 feature-level mixing (L_M-F) to the aggregate baseline (ablation)AGG on PACS · PACS (ResNet-18)average accuracy: 78.5 -> 81.1Improved
add image-level mixing (L_M-IMG) only (ablation)AGG on PACS · PACS (ResNet-18)average accuracy: 78.5 -> 76.3Hurt
add image-level mixing only, Sketch domain (ablation)AGG on PACS · PACS Sketchaccuracy: 69.4 -> 59.5Hurt
add image-level mixing to feature-level mixing (ablation)CuMix without curriculum · PACS (ResNet-18)average accuracy: 81.1 -> 81.2Improved
add curriculum mixing strategy (ablation)CuMix (image+feature mixing) · PACS (ResNet-18)average accuracy: 81.2 -> 81.6Improved
add curriculum mixing strategy, Sketch domain (ablation)CuMix · PACS Sketchaccuracy: 71.5 -> 72.6Improved
add mixing (CuMix) to the ZSL baseline on CUB (ablation)cross-entropy baseline · CUB ZSLaccuracy: 52.4 -> 60.4Improved
add mixing (CuMix) on AWA1 (ablation)cross-entropy baseline · AWA1 ZSLaccuracy: 62.5 -> 64.0 (GFZSL 68.3)Mixed
add CuMix to SPNet for ZSL+DGSPNet · DomainNet ZSL+DGaverage per-class accuracy: 19.4 -> 20.7Improved
add standard mixup to SPNetSPNet · DomainNet ZSL+DGaverage per-class accuracy: 19.4 -> 19.7No clear effect
add DANN to SPNetSPNet · DomainNet ZSL+DGaverage per-class accuracy: 19.4 -> 19.1Hurt
add feature-level mixup to image-level mixup (two-level) (ablation)MixUp img only · DomainNet Real+Painting sourcesaverage per-class accuracy: 14.3 -> 15.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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