新方法让检测模型持续发现未知物体，同时不丢已知类别的识别能力。
Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection
- 用组合式数据挖掘策略找与已知物体差异大的未知样本
- 在两个基准上提升已知类准确率，未知物体召回率提高近2.4倍
- 适合需要长期更新识别能力的开放世界视觉系统
开放世界目标检测（OWOD）通过人工引导实现对未知物体的持续发现与整合，但现有方法常因已知与未知类别语义混淆及灾难性遗忘，导致未知物体召回率下降、已知类别准确率受损。为此，我们提出统一框架CROWD，将未知物体发现与表征学习重构为组合式（集合型）数据发现（CROWD-Discover）与表征学习（CROWD-Learn）任务。CROWD-Discover通过最大化子模条件增益（SCG）函数，有策略地挖掘与已知物体差异显著的未知实例。随后，CROWD-Learn采用新型组合目标，联合解耦已知与未知表征，同时保持已知类间判别一致性，从而缓解混淆与遗忘问题。在多个OWOD基准上的实验证明，该方法在M-OWODB和S-OWODB上分别提升已知类准确率2.83%和2.05%，未知召回率较领先基线提升近2.4倍。
原文摘要 · Abstract (English)
Open-World Object Detection (OWOD) enriches traditional object detectors by enabling continual discovery and integration of unknown objects via human guidance. However, existing OWOD approaches frequently suffer from semantic confusion between known and unknown classes, alongside catastrophic forgetting, leading to diminished unknown recall and degraded known-class accuracy. To overcome these challenges, we propose Combinatorial Open-World Detection (CROWD), a unified framework reformulating unknown object discovery and adaptation as an interwoven combinatorial (set-based) data-discovery (CROWD-Discover) and representation learning (CROWD-Learn) task. CROWD-Discover strategically mines unknown instances by maximizing Submodular Conditional Gain (SCG) functions, selecting representative examples distinctly dissimilar from known objects. Subsequently, CROWD-Learn employs novel combinatorial objectives that jointly disentangle known and unknown representations while maintaining discriminative coherence among known classes, thus mitigating confusion and forgetting. Extensive evaluations on OWOD benchmarks illustrate that CROWD achieves improvements of 2.83% and 2.05% in known-class accuracy on M-OWODB and S-OWODB, respectively, and nearly 2.4x unknown recall compared to leading baselines.
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。