SOURCE-LINKED INTELLIGENCE

Cross-Domain Tracker Adaptation Without Target-Domain Labels via Vision-Language Agents

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

We present a system that uses a Vision-Language Model (VLM) as a diagnostic agent for adapting a detect-to-track pipeline to a new target domain without access to target-domain labels. Rather than optimizing against annotated metrics, the VLM directly inspects rendered tracking outputs, identifies visual failure modes, and recommends parameter updates through an iterative tuning loop. We first demonstrate that ground-truth-supervised hyperparameter transfer can be brittle. On MOT17->MOT20, applying a source-derived oracle configuration reduces mean HOTA by 0.090, from a target-domain ceiling o

Read original source ↗ Open in workspace

recordType

paper

region

Global