AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Keep It Frozen: Domain-Routed Conditional Residual Modulation for Multi-Domain Vision Transformers

Ufaq Khan, Umair Nawaz, Massimo Caputo, Muhammad Bilal, Junaid Qadir, Muhammad Haris Khan

CVPR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation

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 Residual Modulation Blocks to the frozen ViT (ablation)DCRM-ViT · FPUS23Accuracy (%): 51.4 -> 63.4Improved
add Residual Modulation Blocks (ablation)DCRM-ViT · Fetal PlanesAccuracy (%): 74.5 -> 89.3Improved
add Domain Router for soft domain weights (ablation)DCRM-ViT · Fetal PlanesAccuracy (%): 78.2 -> 89.3Improved
add bi-level meta-learning (ablation)DCRM-ViT · Fetal PlanesAccuracy (%): 83.1 -> 89.3Improved
add Parameter Synthesizer Network (ablation)DCRM-ViT · Food101Accuracy (%): 92.2 -> 95.7Improved
add domain-aware attention bias (DAB) (ablation)DCRM-ViT · FPUS23Accuracy (%): 60.1 -> 63.4Improved
add gating channel unit (ablation)DCRM-ViT · FPUS23Accuracy (%): 60.7 -> 63.4Improved
add drop-path regularization (ablation)DCRM-ViT · Food101Accuracy (%): 95.2 -> 95.7No clear effect
use GELU activation component (ablation)DCRM-ViT · SUN397Accuracy (%): 81.1 -> 81.3No clear effect
increase number of RMB modules up to 12 layers (ablation)DCRM-ViT · multi-domain classificationperformanceMixed
replace LoRA with DCRM-ViTfrozen ViT adaptation · Fpus23 (fine-tuned)Accuracy (%): 63.0 -> 63.4Improved
use DCRM-ViT instead of CLIP for zero-shot transferzero-shot classification · CIFAR-10 (zero-shot)Accuracy (%): 71.9 -> 75.2Improved

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