AI Paper Atlas

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

Factors of Influence for Transfer Learning Across Diverse Appearance Domains and Task Types

Thomas Mensink, Jasper Uijlings, Alina Kuznetsova, Michael Gygli, Vittorio Ferrari

TPAMI 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 97 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
start from ILSVRC'12 pre-training instead of training from scratchHRNetV2 transfer models · full target training set, all targetsrelative performance: improves performance by 5%-46%Improved
add an intermediate best source task between ILSVRC'12 and the targetILSVRC'12 pre-trained models · small target training setshare of targets with positive transfer: 85% positive, 67% very positiveImproved
add an intermediate best source task between ILSVRC'12 and the targetILSVRC'12 pre-trained models · full target training setshare of targets with positive transfer: 56% positive, 19% very positiveImproved
use a source from the same image domain instead of a different domain (same task type) (ablation)transfer chains · small target training setshare with positive transfer: 14% -> 69%Improved
use a source of the same task type instead of another task type (different domain) (ablation)transfer chains · small target training setshare with positive transfer: 5% -> 14%Improved
measure domain distance by target-to-closest-source inclusion rather than source-to-closest-target (ablation)domain distance measure · small source small target semantic segmentationKendall tau with transfer gain: 0.06 -> 0.42Improved
compare domain distance to source size as predictor of transfer gain (ablation)small target transfer experiments · semantic segmentationKendall tau with transfer gain: 0.12 -> 0.40Improved
use a larger source than the target dataset (within-domain, within-task) (ablation)transfer chains · small target training setshare with positive transfer: 5% -> 60%Improved
use the largest within-domain source instead of the multi-source model (ablation)semantic segmentation transfer · small target training set, 10 targetstransfer gain: 7 out of 10 significantly betterMixed
use a full target training set instead of a small one (ablation)transfer chains · all source-target pairsshare with positive transfer: 21% -> 14%Hurt
use segmentation source for object detection on the same datasetcross-task transfer · small target training setshare with positive transfer: 100% positiveImproved
use keypoint detection source for segmentation on the same datasetcross-task transfer · small target training setshare with negative transfer: 100% negativeHurt

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