AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Unlocking the Potential of Vision Foundation Models for Multi-Task Dense Prediction via Mixture of Task Adapters

Yunzhi Zhuge, Xinzhuo Yu, Sitong Gong, Lu Zhang, Pingping Zhang, Huchuan Lu

TPAMI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 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 MoTA (task adapters) to frozen backbone (ablation)MTL baseline · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 0.00 -> 6.10Improved
add SPI (semantic prior injector) alone (ablation)MTL baseline · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 0.00 -> 5.66Improved
add SPI on top of MoTA (ablation)MoTA · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 6.10 -> 8.88Improved
add TG-LoRA to MoTA (ablation)MoTA w/o TG-LoRA · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 7.74 -> 8.88Improved
add TA-MoE to MoTA (ablation)MoTA w/o TA-MoE · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 7.97 -> 8.88Improved
insert MoE at QKV and projection instead of none (ablation)TA-MoE · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 7.97 -> 8.88Improved
also insert MoE in FFN beyond QKV+Proj (ablation)TA-MoE · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 8.88 -> 8.68Hurt
place experts in backbone instead of decoder (ablation)D2MoE vs Decoder MoE · PASCAL-Context (frozen DINOv3 ViT-L, matched budget)Delta_m (%): 5.90 -> 8.88Improved
task-aware routing vs shared LoRA at matched budget (ablation)D2MoE · PASCAL-Context (frozen DINOv3 ViT-L, matched budget)Delta_m (%): 8.48 -> 8.88Improved
increase TG-LoRA rank from 2 to 16 (ablation)TG-LoRA · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): 8.07 -> 8.88Improved
increase number of experts from 2 to 16, then 32 (ablation)TA-MoE · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Delta_m (%): peak 8.88 at 16 experts; parsing 78.05 -> 77.64 at 32Mixed
scale backbone ViT-L to ViT-H (ablation)D2MoE · PASCAL-Context (frozen DINOv3 ViT-L, ablation)Saliency maxF: 85.55 -> 83.17Hurt

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