AI Paper Atlas

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

Semi-supervised Deep Transfer for Regression without Domain Alignment

Mainak Biswas, Ambedkar Dukkipati, Devarajan Sridharan

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 0 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 CRAFT unsupervised contradistinguisher loss to supervised transferEEGNet-LSTM TL · Large Grid saccade (1% labels)RMSE: 92.26 -> 84.17Improved
add CRAFT unsupervised loss to supervised transferSFCN TL · TLSA brain age (20% labels)RMSE: 7.41 -> 7.14Improved
add CRAFT loss under biased label sampling with true marginal priorSFCN TL · TLSA brain age (biased sampling)RMSE: 8.40 -> 7.98Improved
add CRAFT unsupervised loss to supervised transferAttn-Resnet TL · JHU-crowd people counting (2% labels)RMSE: 459.05 -> 550.77Hurt
add CRAFT unsupervised loss to supervised transferResnet TL · Camelyon-17 tumor size (1% labels)RMSE: 0.260 -> 0.243Improved
use CRAFT instead of DataFreeEEGNet-LSTM · Large Grid saccade (1% labels)RMSE: 87.64 -> 84.17Improved
use CRAFT instead of MixupEEGNet-LSTM · Large Grid saccade (1% labels)RMSE: 135.70 -> 84.17Improved
use CRAFT instead of DataFreeSFCN · TLSA brain age (20% labels)RMSE: 7.36 -> 7.14Improved
replace Pyramidal CNN with EEGNet-LSTM decodersource/target model · Large Grid saccade (100% labels)RMSE: 63.84 -> 51.47Improved
increase unsupervised loss weight alpha from 0.1 to 1.0 (ablation)CRAFT · TLSA brain age (20% labels)RMSE: 7.14 -> 8.64Hurt
decrease unsupervised loss weight alpha from 0.1 to 0.01 (ablation)CRAFT · TLSA brain age (20% labels)RMSE: 7.14 -> 7.31Mixed
increase alpha from 0.1 to 1.0 (ablation)DataFree · TLSA brain age (20% labels)RMSE: 7.35 -> 8.70Hurt

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