AI Paper Atlas

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

Boomda: Balanced Multi-objective Optimization for Multimodal Domain Adaptation

Jun Sun, Xinxin Zhang, Simin Hong, Jian Zhu, Xiang Gao

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 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
use Boomda instead of CDANmultimodal domain adaptation · IEMOCAP avgweighted F1: 46.95 -> 48.73Improved
use Boomda instead of CDANmultimodal domain adaptation · MSP-IMPROV avgweighted F1: 40.07 -> 41.50Improved
use Boomda instead of PCL on all-modality inputmultimodal domain adaptation · IEMOCAP AVLweighted F1: 49.72 -> 54.82Improved
Boomda versus other methods on acoustic-visualmultimodal domain adaptation · MSP-IMPROV AVweighted F1: DANN 42.44 vs Boomda 40.31Hurt
add correlation alignment (ablation)Boomda · IEMOCAP avgweighted F1: 36.75 -> 45.55Improved
add pseudo labeling by voting (ablation)Boomda · IEMOCAP avgweighted F1: 36.75 -> 45.09Improved
combine correlation alignment and pseudo labeling (ablation)Boomda · IEMOCAP avgweighted F1: 45.55 -> 48.73Improved
use MGDA-based modality-balanced alignment weights instead of equal weights (ablation)Boomda · IEMOCAP avgweighted F1: 46.27 -> 48.73Improved
use balanced alignment weights instead of equal weights (ablation)Boomda · IEMOCAP VLweighted F1: 39.91 -> 42.83Improved
approximate Q with its diagonal matrix for closed-form weights (ablation)Boomda · IEMOCAP trainingratio r of off-diagonal to diagonalNo clear effect
add more modalities to baseline DALN without balancingDALN · IEMOCAPweighted F1: 47.23 -> 45.58Hurt

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