AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation

Xueqi Hu, Xinyue Zhou, Qiusheng Huang, Zhengyi Shi, Li Sun, Qingli Li

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 110 citations (OpenAlex)

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 QS-Attn query selection and feature routingCUT · CityscapesmAP: 24.7 -> 27.9Improved
add QS-Attn query selection and feature routingCUT · CityscapesFID: 54.3 -> 48.8Improved
add QS-Attn query selection and feature routingCUT · Cat→DogFID: 76.2 -> 72.8Improved
add QS-Attn query selection and feature routingCUT · Horse→ZebraSWD: 31.5 -> 30.3Improved
select queries by entropy instead of randomly (ablation)QS-Attn global model · Horse→ZebraFID: 52.1 -> 41.1Improved
use QS-Attn to route selected values (ablation)QS-Attn global model · Horse→ZebraFID: 61.1 -> 41.1Improved
route the source-domain QS-Attn matrix across both domains instead of self-domain routing (ablation)QS-Attn global model · Horse→ZebraFID: 43.3 -> 41.1Improved
select queries by entropy rather than randomly (ablation)QS-Attn with self-domain routing · Horse→ZebraFID: 53.4 -> 43.3Improved
use Informer max-mean query selection instead of entropy selection (ablation)QS-Attn global model · Horse→ZebraFID: 41.1 -> 43.9Hurt
use local attention for both selection and value routing instead of global attention (ablation)QS-Attn · Horse→ZebraFID: 41.1 -> 38.6Improved
use local selection with global value routing instead of global selection and routing (ablation)QS-Attn · Horse→ZebraFID: 41.1 -> 42.3Hurt
apply QS-Attn to all five feature layers instead of the last two (ablation)QS-Attn · Cat→DogFID: 72.8 -> 73.1Hurt

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