用模块化方法提升多目标追踪在不同场景下的泛化能力
Is Multiple Object Tracking a Matter of Specialization?
- 为不同场景属性训练专用轻量模块，按需组合
- 零样本测试下超越传统单一模型，在MOT17和PersonPath22表现更好
- 无需额外推理时间，适合需要快速适配新场景的系统
端到端基于Transformer的追踪器在多数人相关数据集上表现优异。但在异构场景中训练时面临显著挑战，包括负面干扰（模型学习冲突的场景特定参数）和领域泛化能力有限，通常需昂贵微调以适应新领域。为此，我们提出参数高效场景专用追踪架构（PASTA），结合参数高效微调（PEFT）与模块化深度学习（MDL）。具体地，定义关键场景属性（如视角、光照条件），为每类属性训练专用的PEFT模块，这些专家模块在参数空间中组合，实现对新领域的系统性泛化，且不增加推理时间。在MOTSynth上的大量实验，以及在MOT17和PersonPath22上的零样本评估表明，由精选模块构建的神经追踪器优于其单体版本。代码与模型已公开。
原文摘要 · Abstract (English)
End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets. However, training these trackers in heterogeneous scenarios poses significant challenges, including negative interference - where the model learns conflicting scene-specific parameters - and limited domain generalization, which often necessitates expensive fine-tuning to adapt the models to new domains. In response to these challenges, we introduce Parameter-efficient Scenario-specific Tracking Architecture (PASTA), a novel framework that combines Parameter-Efficient Fine-Tuning (PEFT) and Modular Deep Learning (MDL). Specifically, we define key scenario attributes (e.g, camera-viewpoint, lighting condition) and train specialized PEFT modules for each attribute. These expert modules are combined in parameter space, enabling systematic generalization to new domains without increasing inference time. Extensive experiments on MOTSynth, along with zero-shot evaluations on MOT17 and PersonPath22 demonstrate that a neural tracker built from carefully selected modules surpasses its monolithic counterpart. We release models and code.
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。