AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval

Aneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang, Tao Xiang, Yi-Zhe Song

CVPR 2021 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 112 citations (OpenAlex)

Check 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
disentangle shared semantic content from sketch-specific style and meta-train adaptation componentsStyleMeUp · Chair-V2acc.@1: 56.54 -> 62.86Improved
disentangle shared semantic content from sketch-specific style and meta-train adaptation componentsStyleMeUp · Shoe-V2acc.@1: 34.10 -> 36.47Improved
disentangle shared semantic content from sketch-specific style and meta-train adaptation componentsStyleMeUp · Sketchy (ext)mAP: 0.810 -> 0.905Improved
disentangle shared semantic content from sketch-specific style and meta-train adaptation componentsStyleMeUp · TU Berlin (ext)mAP: 0.690 -> 0.778Improved
add explicit sketch-style diversity modeling (ablation)StyleMeUp · Shoe-V2acc.@1: 27.12 -> 36.47Improved
add meta-learned feature-transformation layers (ablation)StyleMeUp · Shoe-V2acc.@1: 33.28 -> 36.47Improved
meta-learn FT parameters instead of fixing them (ablation)StyleMeUp · Shoe-V2acc.@1: 34.18 -> 36.47Improved
add the adaptive disentanglement regulariser (ablation)StyleMeUp · Shoe-V2acc.@1: 32.57 -> 36.47Improved
use one inner-loop update rather than additional updates (ablation)StyleMeUp · QMUL Shoe-V2accuracyHurt
increase embedding dimension beyond 64 (ablation)StyleMeUp · QMUL Shoe-V2accuracyNo clear effect
use the style-agnostic encoder as a feature extractor for sketch classificationStyleMeUp · QuickDrawclassification accuracy: 68.71% -> 75.81%Improved
use meta-learned disentangled sketch representation for sketch-to-sketch retrievalStyleMeUp · QuickDrawmAP: +0.096Improved

Later papers that compared with this method

1 later accepted paper reports StyleMeUp as a baseline in their results tables; 1 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