统一开集目标检测评估标准，解决真实场景中未知物体识别难题
Open-set object detection: towards unified problem formulation and benchmarking
- 构建统一评估框架与新基准数据集，明确未知物体定义
- 在VOC-COCO和OpenImagesRoad上验证最新方法性能提升
- 适合自动驾驶等对可靠性要求高的应用场景研究者
在自动驾驶等高可靠性场景中，准确检测并合理处理训练时未见的类别至关重要。尽管已有多种未知物体检测方法，但普遍存在数据集、评价指标与评测场景不一致的问题，且缺乏对未知物体的清晰定义，导致评估难以比较。为此，本文提出两个新基准：统一的VOC-COCO评估方案与全新的OpenImagesRoad基准，后者提供清晰的层级物体定义及新评价指标。结合自监督视觉变压器在伪标签生成上的进展，改进基于伪标签的开集目标检测（OSOD）方法，提出OW-DETR++。在新基准上对当前最先进方法进行系统评估，明确了问题定义，确保评估一致性，并得出了关于各类OSOD策略有效性的新结论。
原文摘要 · Abstract (English)
In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object detection approaches, we have observed widespread inconsistencies among them regarding the datasets, metrics, and scenarios used, alongside a notable absence of a clear definition for unknown objects, which hampers meaningful evaluation. To counter these issues, we introduce two benchmarks: a unified VOC-COCO evaluation, and the new OpenImagesRoad benchmark which provides clear hierarchical object definition besides new evaluation metrics. Complementing the benchmark, we exploit recent self-supervised Vision Transformers performance, to improve pseudo-labeling-based OpenSet Object Detection (OSOD), through OW-DETR++. State-of-the-art methods are extensively evaluated on the proposed benchmarks. This study provides a clear problem definition, ensures consistent evaluations, and draws new conclusions about effectiveness of OSOD strategies.
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。