用轻量MLP融合模块提升Siamese追踪的精度与效率
Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Tracking
- 设计基于MLP的融合模块，实现像素级交互且结构简单
- 通过分层搜索与可微架构搜索，使模型在宽通道下仍保持低计算开销
- 在多个通用与航拍追踪数据集上达到顶尖性能，适合边缘设备部署
基于卷积或Transformer的Siamese视觉追踪器虽不断进步，但在资源受限硬件上难以高效实现像素级交互，导致精度与效率失衡。为此，我们重新设计了Siamese颈部结构，引入一种简单高效的基于MLP的融合模块，可在极小结构开销下实现像素级交互。然而，直接堆叠MLP块会导致计算成本随通道宽度呈平方级增长。为此，我们构建了一个精心设计的分层搜索空间，并提出定制化的松弛策略，使可微神经架构搜索（DNAS）能将通道宽度优化与其他架构选择解耦。该解耦机制自动平衡通道宽度与深度，生成低复杂度结构。最终追踪器在四个通用和三个航拍追踪基准上均达到最先进水平，同时在资源受限的GPU与NPU上保持实时性能。
原文摘要 · Abstract (English)
Siamese visual trackers have recently advanced through increasingly sophisticated fusion mechanisms built on convolutional or Transformer architectures. However, both struggle to deliver pixel-level interactions efficiently on resource-constrained hardware, leading to a persistent accuracy-efficiency imbalance. Motivated by this limitation, we redesign the Siamese neck with a simple yet effective Multilayer Perception (MLP)-based fusion module that enables pixel-level interaction with minimal structural overhead. Nevertheless, naively stacking MLP blocks introduces a new challenge: computational cost can scale quadratically with channel width. To overcome this, we construct a hierarchical search space of carefully designed MLP modules and introduce a customized relaxation strategy that enables differentiable neural architecture search (DNAS) to decouple channel-width optimization from other architectural choices. This targeted decoupling automatically balances channel width and depth, yielding a low-complexity architecture. The resulting tracker achieves state-of-the-art accuracy-efficiency trade-offs. It ranks among the top performers on four general-purpose and three aerial tracking benchmarks, while maintaining real-time performance on both resource-constrained Graphics Processing Units (GPUs) and Neural Processing Units (NPUs).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。