AI Paper Atlas

Research map / Detection and segmentation / CNN features

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

Yinan He, Gengshi Huang, Siyu Chen, Jianing Teng, Kun Wang, Zhenfei Yin, Lu Sheng, Ziwei Liu, Yu Qiao, Jing Shao

ECCV 2022 · Detection and segmentation › CNN features · approach: Convolution-transformer backbones · 9 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 reconciliation layers in expansion stage (ablation)X-Learner · 10 classification datasets (linear probe)average accuracy (%): 74.8 -> 77.1Improved
add reconciliation layers in expansion stage (ablation)X-Learner · PASCAL VOC07 detectionmAP: 83.9 -> 84.4Improved
use X-Learner instead of hard-sharing multi-taskResNet-50 · 10 classification datasets (linear probe)average accuracy (%): 73.2 -> 77.1Improved
add extra pre-distillation hints (X-Learner++)X-Learner · PASCAL VOC07 detectionmAP: 84.4 -> 84.8Improved
add semantic segmentation task and sourcesX-Learner · PASCAL VOC12 segmentationmIoU: 77.1 -> 77.6Improved
add semantic segmentation task and sourcesX-Learner · PASCAL VOC07 detectionmAP: 84.4 -> 84.3Hurt
add classification sources (CompCars, Dogs)Hard-sharing · ImageNet pre-training accuracyaccuracy (%): 75.0 -> 73.7Hurt
add classification sources (CompCars, Dogs)X-Learner · 10 classification datasets (linear probe)average accuracy (%): 77.1 -> 80.6Improved
reverse order to squeeze then expand (ablation)X-Learner · 10 classification datasets (linear probe)average accuracy (%): 77.1 -> 73.9Hurt
feed reconciliation layers from deeper layers instead of lower layers (ablation)X-Learner · PASCAL VOC07 detectionmAP: 84.4 -> 83.5Hurt
replace distillation with pruning in squeeze stage (ablation)X-Learner · 10 classification datasets (linear probe)average accuracy (%): 77.1 -> 77.2No clear effect
replace distillation with pruning in squeeze stage (ablation)X-Learner · PASCAL VOC07 detectionmAP: 84.4 -> 83.1Hurt

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