AI Paper Atlas

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

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-Based Image Retrieval

Anjan Dutta, Zeynep Akata

IJCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 30 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 cycle consistency loss to adversarial-only training (ablation)SEM-PCYC · Sketchy (Extended) zero-shotmAP@all: 0.128 -> 0.147Improved
add classification loss to adversarial-only training (ablation)SEM-PCYC · Sketchy (Extended) zero-shotmAP@all: 0.128 -> 0.140Improved
add cycle consistency and classification losses together (adversarial on sketch and image) (ablation)SEM-PCYC · Sketchy (Extended) zero-shotmAP@all: 0.128 -> 0.213Improved
add adversarial loss for the semantic domain (ablation)SEM-PCYC · Sketchy (Extended) zero-shotmAP@all: 0.213 -> 0.349Improved
add the l2,1-regularized auto-encoder regularizer for side information (ablation)SEM-PCYC · Sketchy (Extended) zero-shotmAP@all: 0.323 -> 0.349Improved
add auto-encoder side-information selection (compress to 64d) (ablation)SEM-PCYC · Sketchy (Extended) zero-shotmAP@all: 0.382 -> 0.349Hurt
add auto-encoder side-information selection (compress to 64d) (ablation)SEM-PCYC · QuickDraw (Extended) zero-shotmAP@all: 0.185 -> 0.177Hurt
swap VGG-16 features for SE-ResNet-50 (FastText, 64d) (ablation)SEM-PCYC · Sketchy (Extended) zero-shotmAP@all: 0.344 -> 0.368Improved
swap VGG-16 features for SE-ResNet-50 (FastText, 64d) (ablation)SEM-PCYC · TU-Berlin (Extended) zero-shotmAP@all: 0.262 -> 0.349Improved
combine Word2Vec text embedding with Jiang-Conrath hierarchical embedding (ablation)SEM-PCYC · Sketchy (Extended) zero-shot, 64dmAP@all: 0.330 -> 0.349Improved
remove 5% to 30% of side-information dimensions (ablation)SEM-PCYC · zero-shot SBIRmAP@all: 5% to 30%Improved
remove more than 20% to 40% of side information (ablation)SEM-PCYC · zero-shot SBIRmAP@all: beyond 20% to 40%Hurt

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