AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

G2D: Boosting Multimodal Learning with Gradient-Guided Distillation

Mohammed Rakib, Arunkumar Bagavathi

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 4 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 SMP (ablation)G2D loss · CREMA-Daccuracy (%): 78.63 -> 85.89Improved
add SMP (ablation)G2D loss · AV-MNISTaccuracy (%): 72.76 -> 73.03Improved
add SMP (ablation)G2D loss · UR-Funnyaccuracy (%): 63.78 -> 65.49Improved
add SMP (ablation)Joint-Train · CREMA-Daccuracy (%): 67.47 -> 80.78Improved
add SMP (ablation)UMT · CREMA-Daccuracy (%): 67.61 -> 82.39Improved
add G2D loss (feature+logit distillation) instead of UMT loss (ablation)SMP training · CREMA-Daccuracy (%): 67.61 -> 78.63Improved
use complete suppression (SMP) instead of partial suppression (ablation)G2D · CREMA-Daccuracy (%): 81.99 -> 85.89Improved
use complete suppression (SMP) instead of partial suppression (ablation)G2D · VGGSoundaccuracy (%): 51.16 -> 53.82Improved
use late fusion instead of FiLM (ablation)G2D · VGGSoundaccuracy (%): 48.11 -> 53.82Improved
use late fusion instead of Sum (ablation)G2D · CREMA-Daccuracy (%): 81.59 -> 85.89Improved
use cross-attention instead of late fusion (ablation)G2D · CREMA-Daccuracy (%): 85.89 -> 85.35Hurt
increase tau1 dedicated epochs for weak modality from 0 to 150 (ablation)G2D · CREMA-Daccuracy (%): 78.63 -> 85.89Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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