AI Paper Atlas

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

Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning

Maunil R Vyas, Hemanth Venkateswara, Sethuraman Panchanathan

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 146 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 SR-Loss semantic relationship regularization (vs F-GAN) on unseen-class confidenceLsrGAN · AWA (GZSL)average softmax confidence on unseen classes: 0.29 -> 0.69Improved
add SR-Loss (vs F-GAN) on unseen-class confidenceLsrGAN · CUB (GZSL, attributes)average softmax confidence on unseen classes: 0.33 -> 0.60Improved
add SR-Loss (vs F-GAN) on unseen-class confidenceLsrGAN · SUN (GZSL)average softmax confidence on unseen classes: 0.32 -> 0.65Improved
add SR-Loss (vs F-GAN) on seen-class confidenceLsrGAN · AWA (GZSL)average softmax confidence on seen classes: 0.86 -> 0.83Hurt
add SR-Loss (vs F-GAN) on seen-class confidenceLsrGAN · SUN (GZSL)average softmax confidence on seen classes: 0.35 -> 0.39Improved
add SR-Loss and related components versus LisGAN, ZSLLsrGAN · AWA (attributes, ZSL)Top-1 accuracy: 70.6 -> 66.4Hurt
LsrGAN versus LisGAN on GZSL harmonic meanLsrGAN · CUB (attributes, GZSL)harmonic mean: 51.6 -> 53.0Improved
LsrGAN versus GAZSL on Wikipedia CUB Hard ZSLLsrGAN · CUB Hard (Wikipedia, ZSL)Top-1 accuracy: 10.3 -> 14.2Improved
LsrGAN versus GAZSL on Wikipedia CUB Easy GZSLLsrGAN · CUB Easy (Wikipedia, GZSL)seen-unseen AUC: 35.4 -> 39.5Improved
LsrGAN versus GAZSL on NAB Hard GZSLLsrGAN · NAB Hard (Wikipedia, GZSL)seen-unseen AUC: 5.8 -> 6.4Improved
add visual pivot regularizer and SR-Loss, and denoiser (ablation S1-S4, values only in Fig. 4a) (ablation)LsrGAN · CUB (ZSL ablation)Top-1 accuracyImproved
vary soft margin epsilon of SR-Loss (ablation)LsrGAN · SR-Loss parameter sensitivityaccuracyMixed

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