AI Paper Atlas

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

FREE: Feature Refinement for Generalized Zero-Shot Learning

Shiming Chen, Wenjie Wang, Beihao Xia, Qinmu Peng, Xinge You, Feng Zheng, Ling Shao

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 255 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 FR with SAMC-loss to the baseline (ablation)re-implemented f-VAEGAN · CUBharmonic mean H: 53.1 -> 56.5Improved
add FR with semantic cycle-consistency loss to the baseline (ablation)re-implemented f-VAEGAN · CUBharmonic mean H: 53.1 -> 55.7Improved
add FR with SAMC-loss to the baseline (ablation)re-implemented f-VAEGAN · FLOharmonic mean H: 64.9 -> 72.0Improved
add FR with semantic cycle-consistency loss to the baseline (ablation)re-implemented f-VAEGAN · FLOharmonic mean H: 64.9 -> 68.1Improved
add FR with SAMC-loss to the baseline (ablation)re-implemented f-VAEGAN · AWA2harmonic mean H: 62.7 -> 65.2Improved
add FR with semantic cycle-consistency loss to the baseline (ablation)re-implemented f-VAEGAN · AWA2harmonic mean H: 62.7 -> 64.4Improved
add semantic cycle-consistency loss to FR with SAMC-loss (ablation)FREE · CUBharmonic mean H: 56.5 -> 57.7Improved
add semantic cycle-consistency loss to FR with SAMC-loss (ablation)FREE · FLOharmonic mean H: 72.0 -> 75.0Improved
add SAMC-loss to FR with semantic cycle-consistency loss (ablation)FREE · AWA2harmonic mean H: 64.4 -> 67.1Improved
add full FR (both losses) to the baseline (ablation)re-implemented f-VAEGAN · CUB, FLO, AWA2harmonic mean H: +4.6%, +10.1%, +4.4%Improved
use SAMC-loss instead of semantic cycle-consistency loss alone in FR (ablation)FREE · CUB, FLO, AWA2harmonic mean H: 55.7 -> 56.5Improved
replace fine-tuning with feature refinementf-VAEGAN · FLOharmonic mean H: 75.1 -> 75.0No clear effect

Later papers that compared with this method

5 later accepted papers report FREE as a baseline in their results tables; 3 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