让视觉语言检测器在测试时快速适应新场景，效果更好且开销小。
VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
- 利用重叠框和图像提示动态调整检测，减少错误聚集。
- 在艺术风格、弱光等10种分布偏移下，精度提升3.2~6.8个百分点。
- 适合需要实时部署的检测系统，尤其关注低资源环境应用。
视觉语言目标检测器（如 YOLO-World 和 Grounding DINO）具备出色的零样本泛化能力，但在分布偏移下性能下降。测试时自适应（TTA）通过仅使用无标签目标数据，在推理阶段进行模型调整，是一种实用方案。然而，现有 TTA 方法在视觉语言检测任务中仍较少探索。此前方法依赖均值教师框架，带来显著延迟与内存开销。为此，我们提出 VLOD-TTA，一种基于密集提议重叠与图像条件提示的低开销 TTA 方法。该方法结合：(i) IoU加权熵目标，强化空间连贯性提议簇，缓解孤立框导致的确认偏差；(ii) 图像级兼容性排序提示，聚合最有效提示得分用于检测。在多种分布偏移场景（包括艺术领域、恶劣驾驶条件、低光照图像及常见损坏）下的实验表明，VLOD-TTA 在 YOLO-World 与 Grounding DINO 上均持续优于标准 TTA 基线和先前最优方法，平均提升达 3.2~6.8%。代码已开源。
原文摘要 · Abstract (English)
Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt models during inference using only unlabeled target (test) data. However, while TTA has made substantial progress in vision-language classification, its application to VLODs remains largely unexplored. The only prior method relies on a mean-teacher framework that introduces significant latency and memory overhead. To this end, we introduce VLOD-TTA, a TTA method that leverages dense proposal overlap and image-conditioned prompts to adapt VLODs with low additional overhead. VLOD-TTA combines (i) an IoU-weighted entropy objective that emphasizes spatially coherent proposal clusters and mitigates confirmation bias from isolated boxes, and (ii) image-conditioned prompt selection that ranks prompts by image-level compatibility and aggregates the most informative prompt scores for detection. Our experiments across diverse distribution shifts, including artistic domains, adverse driving conditions, low-light imagery, and common corruptions, indicate that VLOD-TTA consistently outperforms standard TTA baselines and the prior state-of-the-art method using YOLO-World and Grounding DINO. Our code: https://github.com/imatif17/VLOD-TTA
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。