发表机构
Indraprastha Institute of Information Technology Delhi（因德拉普拉斯信息技术学院德里分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出自路由张量适配器（SRTA），无需外部门控网络即可实现样本特定适配，在多领域视觉分类基准上，以更少参数达到与MoE式PEFT基线相当或更优的平均准确率。
AI 中文摘要
通用视觉表示需要适配机制，使其能跨异构领域适配，且不会将知识拆分为特定领域的模块。参数高效微调可高效适配冻结的视觉基础模型，但标准低秩适配器对所有输入使用固定子空间，当领域在风格、背景和语义上下文存在差异时，这种方式会受限。基于MoE的适配器通过多个专家路径提升专业化程度，但通常依赖外部路由器和大型专家库，会增加参数并使路由与适配分离。我们提出**自路由张量适配器（Self-Routed Tensor Adapters，SRTA）**，这是一种用于多领域视觉适配的紧凑框架。SRTA将每个输入投影到低秩空间，利用可学习的领域矩阵从该表示计算路由权重，并使用这些权重混合共享Tucker核的切片。这无需外部门控网络即可生成样本特定的适配矩阵，使共享视觉因子可重复使用，同时支持领域感知的专业化。为强化路径学习，我们引入渐进式深度加权路由目标，对适配器层的路由决策进行监督。在五个异构多领域视觉分类基准上，SRTA的平均准确率与MoE式参数高效微调（PEFT）基线相当或略高，同时使用的可训练参数显著更少。在秩为64时，SRTA在4领域设置中使用277万参数，而MoLoRA为952万；在6领域设置中，SRTA使用300万参数，MoLoRA为1431万。总体而言，SRTA为将视觉基础模型适配为通用多领域表示提供了有效的准确率-参数权衡方案。GitHub
英文摘要
Universal visual representations require adaptation mechanisms that adapt across heterogeneous domains without fragmenting knowledge into domain-specific modules. Parameter-efficient fine-tuning adapts frozen visual foundation models efficiently, but standard low-rank adapters use a fixed subspace for all inputs, which can be restrictive when domains differ in style, background, and semantic context. MoE-based adapters improve specialization through multiple expert pathways, but often rely on external routers and large expert banks, adding parameters and separating routing from adaptation. We propose \textbf{Self-Routed Tensor Adapters}, a compact framework for multi-domain visual adaptation. SRTA projects each input into a low-rank space, computes routing weights from this representation using a learnable domain matrix, and uses these weights to blend slices of a shared Tucker core. This produces a sample-specific adaptation matrix without an external gating network, allowing shared visual factors to be reused while supporting domain-aware specialization. To strengthen pathway learning, we introduce a progressive depth-weighted routing objective that supervises routing decisions across adapter layers. Across five heterogeneous multi-domain visual classification benchmarks, SRTA achieves competitive or slightly stronger average accuracy than MoE-style PEFT baselines while using substantially fewer trainable parameters. At rank 64, SRTA uses 2.77M parameters in the 4-domain setting compared with 9.52M for MoLoRA, and 3.00M in the 6-domain setting compared with 14.31M. Overall, SRTA offers an effective accuracy-parameter trade-off for adapting visual foundation models toward universal multi-domain representations. \href{https://github.com/surajyadav-research/SRTA}{GitHub}
CommentsAccepted at ECCV Workshop 2026 (Archival Track)
