让开放词汇目标检测更准：用推理时校准提升定位精度
ProCal: Inference-Time Proposal Calibration for Open-Vocabulary Object Detection
- 推理时通过前景感知与背景抑制双重评分，校准候选框置信度
- 在OV-LVIS数据集上，平均召回率提升2.5个百分点（APr）
- 适合做开放词汇检测的算法优化，尤其关注定位准确性的研究者
开放词汇目标检测旨在定位并分类训练中未见的物体类别。近期方法利用冻结的视觉语言模型（VLM）作为检测主干，提升对未知类别的识别能力。然而，VLM分类分数无法有效捕捉物体在图像中的位置和尺度信息。我们观察到预训练VLM能区分前景与背景区域。基于此，提出一种简单的推理时候选框校准方法（ProCal），通过结合两种得分——定位感知前景得分与背景感知抑制得分——来提升分类分数的定位质量。定位感知前景得分反映候选框是否包含物体区域；背景感知抑制得分衡量候选框与背景的相似程度。分析表明，ProCal可有效抑制背景候选框上的虚假新类别激活，并将真实新类别候选框排在背景及部分新类别候选框之上。应用于CLIPSelf ViT-L/14，在OV-LVIS上使APr提升2.5个百分点。分析显示，该方法通过候选框级定位感知重排序，缓解了新类别排名偏差问题。
原文摘要 · Abstract (English)
Open-vocabulary object detection aims to localize and classify objects beyond the fixed set of categories seen dur ing training. Recent open-vocabulary object detection methods improve localization and classification for unseen categories by leveraging a frozen VLM as a detector backbone. However, VLM classification score lacks recognizing position and scale of the object in an image. We observe that pretrained VLMs en able to classify foreground and background regions. According to this observation, we propose a simple inference-time Pro posal Calibration (ProCal) that improves localization quality of the classification score. ProCal computes a proposal prior by combining two scores: localization-aware foreground score and background-aware suppression score. Localization-aware foreground score captures whether a proposal contains an object area. Background-aware suppression score measures the extent to which the proposal resembles background. We analyze that ProCal suppresses false novel activation on background proposals and consistently ranks true novel proposals above background and partial novel proposals. Applied to CLIPSelf ViT-L/14, ProCal improves APr +2.5 on OV-LVIS. The analyses show that proposal-level localization-aware reranking effects to mitigate ranking miscalibration for novel objects.
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。