AI Paper Atlas

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

Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization

Shujun Wang, Lequan Yu, Caizi Li, Chi-Wing Fu, Pheng-Ann Heng

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 210 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 extrinsic momentum metric learning to baseline (ablation)DeepAll ResNet-50 · PACS averageaccuracy: 81.15 -> 84.14Improved
add intrinsic jigsaw self-supervision to baseline (ablation)DeepAll ResNet-50 · PACS averageaccuracy: 81.15 -> 83.88Improved
combine extrinsic and intrinsic supervision (ablation)EISNet ResNet-50 · PACS averageaccuracy: 84.14 -> 85.84Improved
use semi-hard negative selector instead of random (ablation)EISNet AlexNet · PACS Sketchaccuracy: 65.38 -> 68.08Improved
use K-hard negative selector instead of semi-hard (ablation)EISNet AlexNet · PACS Sketchaccuracy: 68.08 -> 70.25Improved
increase memory bank size from 128 to 1024 (K 32 to 256) (ablation)EISNet AlexNet · PACS Sketchaccuracy: 67.93 -> 70.25Improved
increase K from 256 to 512 (ablation)EISNet AlexNet · PACS SketchaccuracyHurt
use large momentum coefficient 0.999 for MuEncoder (ablation)EISNet AlexNet · PACS SketchaccuracyImproved
EISNet instead of MASF with ResNet-50MASF · PACS averageaccuracy: 82.67 -> 85.84Improved
EISNet instead of MASF with AlexNetMASF · VLCS averageaccuracy: 74.11 -> 74.67Improved
EISNet instead of MASF with ResNet-18MASF · PACS averageaccuracy: 81.04 -> 82.15Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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