AI Paper Atlas

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

TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning

Xin Wang, Fisher Yu, Ruth Wang, Trevor Darrell, Joseph E. Gonzalez

CVPR 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 114 citations (OpenAlex)

Check 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 the embedding loss (ablation)TAFE-Net · CUB GZSLharmonic mean (H): 45.4 -> 49.2Improved
Add the embedding loss (ablation)TAFE-Net · AWA1 GZSLharmonic mean (H): 58.8 -> 63.2Improved
Add the embedding loss (ablation)TAFE-Net · AWA2 GZSLharmonic mean (H): 47.2 -> 52.2Improved
Add the embedding loss (ablation)TAFE-Net · aPY GZSLharmonic mean (H): 30.5 -> 36.8Improved
Add the embedding loss (ablation)TAFE-Net · SUN GZSLharmonic mean (H): 33.1 -> 33.0No clear effect
Use one-hot task IDs instead of word2vec (ablation)TAFE-Net with ResNet-101 features · MITStates unseen attribute-object pairsAP: 16.2 -> 16.1No clear effect
Use one-hot task IDs instead of word2vec (ablation)TAFE-Net with VGG-16 features · MITStates unseen attribute-object pairsAP: 16.3 -> 16.3No clear effect
Use one-hot task IDs instead of word2vec (ablation)TAFE-Net with VGG-19 features · MITStates unseen attribute-object pairsAP: 15.6 -> 16.3No clear effect
Use VGG-19 rather than ResNet-101 features with word2vec task encoding (ablation)TAFE-Net · MITStates unseen attribute-object pairsAP: 16.2 -> 15.6No clear effect
Use task-conditioned feature embeddings rather than a shared generic embeddingTAFE-Net · MITStates unseen attribute-object pairsAP: +5.9Improved
Use task-conditioned feature embeddings rather than a shared generic embeddingTAFE-Net · StanfordVRD unseen SPO tripletsAP: +6.5Improved
Use TAFE-Net rather than the strongest listed meta-learning baselineImageNet few-shot classification · ImageNet few-shot (n=1)all top-5 accuracy: 54.4 -> 55.7Improved

Later papers that compared with this method

1 later accepted paper reports TAFE-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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