AgentDet：一种用于零样本/少样本目标检测的共享黑板多智能体框架
AgentDet: A Shared-Blackboard Multi-Agent Framework for Zero-/Few-Shot Object Detection
提出共享黑板多智能体框架，将检测解耦为四个协作角色，仅训练Agent-Judge的图像编码器和基于LLM的检测头，为视觉研究者提供了一种轻量级、可泛化到新类别的零/少样本检测新范式。
原文依据 AgentDet decouples detection into four cooperating roles--Agent-Scout, Agent-Pinner, Agent-Curator, and Agent-Judge
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大型多模态语言模型在视觉-语言任务上取得了快速进展，然而它们在封闭目标类别集下的零样本/少样本目标检测（ZSOD/FSOD）潜力尚未被充分探索。ZSOD/FSOD受限于数据稀缺和灾难性遗忘。尽管视觉-语言模型（VLM）在多个基准上表现出优异性能，但它们通常依赖大规模视觉预训练，这与FSOD在有限监督下测试对新类别泛化的目标不一致。我们提出AgentDet，一种共享黑板多智能体框架，通过伪增量学习统一ZSOD和FSOD。AgentDet将检测解耦为四个协作角色——Agent-Scout、Agent-Pinner、Agent-Curator和Agent-Judge——它们协同维护共享黑板和知识库。为了高效，我们仅通过更新Agent-Judge的图像编码器和基于LLM的检测头来训练Agent-Judge，这是一种轻量级方案，鼓励对先前未见类别的泛化。在PASCAL VOC和MS COCO的ZSOD/FSOD数据集上，AgentDet在多个设置下取得了与最优结果强烈竞争的性能。
英文原文摘要 1212 字符
Large multimodal language models have made rapid progress on vision-language tasks, yet their potential for zero-/few-shot object detection (ZSOD/FSOD) under a closed set of target classes has yet to be fully explored.. ZSOD/FSOD is hampered by data scarcity and catastrophic forgetting. Although vision-language models (VLMs) demonstrated excellent performance on multiple benchmarks, they typically rely on large-scale visual pre-training, which is inconsistent with the goal of FSOD to test generalization to new categories under limited supervision. We introduce AgentDet, a shared-blackboard multi-agent framework that unifies ZSOD and FSOD via pseudo-incremental learning. AgentDet decouples detection into four cooperating roles--Agent-Scout, Agent-Pinner, Agent-Curator, and Agent-Judge--which collaboratively maintain a Shared Blackboard and a Knowledge Base. For efficiency, we only train Agent-Judge by updating its image encoder and LLM-based detection head, which is a lightweight recipe that encourages generalization to previously unseen categories. On PASCAL VOC and MS COCO ZSOD/FSOD datasets, AgentDet achieves strongly competitive performance with state-of-the-art results in several settings.