AI Paper Atlas

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

Label-Embedding for Image Classification

Zeynep Akata, Florent Perronnin, Zaïd Harchaoui, Cordelia Schmid

TPAMI 2016 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 788 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
use continuous attribute embeddings instead of binary {-1,+1} (ablation)ALE · AWA zero-shot (64K FV)top-1 accuracy (%): 41.8 -> 48.5Improved
use continuous attribute embeddings instead of binary {-1,+1} (ablation)ALE · CUB zero-shot (64K FV)top-1 accuracy (%): 19.6 -> 26.9Improved
add mean-centering of output embeddings (ablation)ALE · AWA zero-shot (64K FV)top-1 accuracy (%): 48.5 -> 47.7No clear effect
add l2-normalization of output embeddings (ablation)ALE · AWA zero-shot (64K FV, continuous)top-1 accuracy (%): 44.9 -> 48.5Improved
add l2-normalization of output embeddings (ablation)ALE · CUB zero-shot (64K FV, continuous)top-1 accuracy (%): 22.7 -> 26.9Improved
use ranking objective instead of ridge regression (ablation)ALE · AWA zero-shottop-1 accuracy (%): 44.5 -> 48.5Improved
use ranking objective instead of ridge regression (ablation)ALE · CUB zero-shottop-1 accuracy (%): 21.6 -> 26.3Improved
use ALE instead of DAPDAP · CUB zero-shottop-1 accuracy (%): 12.3 -> 26.9Improved
use ALE instead of DAPDAP · AWA zero-shottop-1 accuracy (%): 41.0 -> 48.5Improved
use ALE instead of DAP for attribute predictionDAP · CUB zero-shotattribute AUC (%): 64.8 -> 59.4Hurt
replace attribute embeddings with Word2Vec (WLE) (ablation)ALE · AWA zero-shottop-1 accuracy (%): 48.5 -> 32.5Hurt
combine attributes and hierarchies with late fusion (AHLE late)ALE · AWA zero-shottop-1 accuracy (%): 48.5 -> 49.4Improved

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