Problem
Research questions and friction points this paper is trying to address.
Multi-Task Dense Prediction
Task-State Adaptation
Prototype Memory
Task-State Adaptation with Prototype Memory for Multi-Task Dense Prediction
🤖 AI Summary
为解决多任务密集预测中不同任务适应需求问题，提出MemMTL框架，通过全局视觉上下文估计任务状态并利用原型记忆进行优化。
📝 Abstract
Vision foundation backbones provide strong representations for dense prediction, yet a single shared feature still needs to support tasks with different, image-dependent adaptation requirements. We propose MemMTL, a multi-task dense prediction framework that estimates a compact task state from global visual context and refines it through a learnable task-state prototype memory. The refined state is converted into task-conditioned expert logits and combined with token-level logits before sparse top-$k$ selection over a local expert bank shared by all tasks. A separate task-agnostic residual bank provides a common adaptation path, and both paths are added once to the backbone feature before task-specific prediction. We specify a matched evaluation protocol on NYUD-v2 and PASCAL-Context with SAM 3 and ViT-L backbones to measure predictive quality, computational cost, and the contributions of task-state conditioning, prototype retrieval, and sparse routing. The numerical record in the present working draft predates this canonical implementation and must be regenerated before it can support empirical claims.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-task Dense Prediction
Prototype Memory
Task-state Adaptation
Sparse Top-$k$ Selection
🔎 Similar Papers
No similar papers found.
