Large Vision-Language Models (LVLMs) have demonstrated remarkable success in a broad range of vision-language tasks, such as general visual question answering and optical character recognition (OCR). However, their performance on perception-centric tasks -- such as object detection, semantic segmentation, and depth estimation -- remains significantly inferior to that of task-specific expert models. For example, Qwen2.5-VL-7B-Instruct achieves only 19% mAP on COCO2017 val, particularly struggling with dense scenes and small object recall. In this work, we introduce Chain-of-Thought for Detection (CoT4Det), a simple but efficient strategy that reformulates perception tasks into three interpretable steps: classification, counting, and grounding -- each more naturally aligned with the reasoning capabilities of LVLMs. Extensive experiments demonstrate that our method significantly improves perception performance without compromising general vision language capabilities. With a standard Qwen2.5-VL-7B-Instruct, CoT4Det boosts mAP from 19.0% to 33.0% on COCO2017 val and achieves competitive results across a variety of perception benchmarks, outperforming baselines by +2% on RefCOCO series and 19% on Flickr30k entities.

翻译：大规模视觉语言模型（LVLMs）在广泛的视觉语言任务中取得了显著成功，例如通用视觉问答和光学字符识别（OCR）。然而，它们在感知中心任务（如目标检测、语义分割和深度估计）上的性能仍然显著低于任务特定的专家模型。例如，Qwen2.5-VL-7B-Instruct在COCO2017验证集上仅达到19%的mAP，尤其在密集场景和小目标召回方面表现不佳。在本工作中，我们引入了检测思维链（CoT4Det），这是一种简单而高效的策略，将感知任务重新表述为三个可解释的步骤：分类、计数和定位——每一步都更自然地与LVLMs的推理能力对齐。大量实验表明，我们的方法在不损害通用视觉语言能力的前提下，显著提升了感知性能。使用标准的Qwen2.5-VL-7B-Instruct，CoT4Det在COCO2017验证集上将mAP从19.0%提升至33.0%，并在多种感知基准测试中取得了有竞争力的结果，在RefCOCO系列上超越基线+2%，在Flickr30k实体上超越19%。