AI Paper Atlas

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

Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval

Qing Liu, Lingxi Xie, Huiyu Wang, Alan L. Yuille

ICCV 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 131 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 teacher-distillation loss L_T to benchmark loss (ablation)SAKE (CSE-ResNet-50) · TU-Berlin Ext. ZS-SBIR 64-dmAP@all: 0.353 -> 0.426Improved
add semantic-aware term (L_SAKE instead of L_T) (ablation)SAKE (CSE-ResNet-50) · TU-Berlin Ext. ZS-SBIR 64-dmAP@all: 0.426 -> 0.434Improved
add L_SAKE to benchmark loss (ablation)ResNet-50 · TU-Berlin Ext. ZS-SBIR 64-dmAP@all: 0.352 -> 0.413Improved
add L_SAKE to benchmark loss (ablation)AlexNet · TU-Berlin Ext. ZS-SBIR 64-dmAP@all: 0.267 -> 0.275Improved
add L_SAKE to benchmark loss (ablation)CSE-ResNet-50 · TU-Berlin Ext. ZS-PBIR 64-dmAP@all: 0.558 -> 0.683Improved
add L_T to benchmark loss (ablation)ResNet-50 · TU-Berlin Ext. ZS-PBIR 64-dmAP@all: 0.542 -> 0.666Improved
add semantic term lambda2 without teacher signal (lambda1=0) (ablation)SAKE · TU-Berlin Ext. ZS-SBIRmAP@all: 0.362 -> 0.370No clear effect
add semantic term lambda2=0.3 with teacher (lambda1=1) (ablation)SAKE · TU-Berlin Ext. ZS-SBIRmAP@all: 0.426 -> 0.434Improved
raise lambda2 from 0.3 to 3 (lambda1=1) (ablation)SAKE · TU-Berlin Ext. ZS-SBIRmAP@all: 0.434 -> 0.412Hurt
raise lambda_SAKE from 1 to 3 (ablation)SAKE · TU-Berlin Ext. ZS-SBIRmAP@all: 0.434 -> 0.429Hurt
raise lambda_SAKE from 0 to 3 on ImageNet categories (ablation)SAKE · TU-Berlin Ext. ZS-PBIR (IN)mAP@all: 0.545 -> 0.758Improved
fine-tune AlexNet with SAKE instead of benchmark loss only (ImageNet top-1 accuracy) (ablation)AlexNet · ImageNet linear-probe top-1 (%)mAP@all: 45.54 -> 51.39Improved

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