⚠️ 以下所有内容总结都来自于 大语言模型的能力，如有错误，仅供参考，谨慎使用
🔴 请注意：千万不要用于严肃的学术场景，只能用于论文阅读前的初筛！
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ，还请您给我们一些鼓励！⭐️ HuggingFace免费体验
2025-05-25 更新
Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundary
Authors:Zhaowei Wu, Binyi Su, Qichuan Geng, Hua Zhang, Zhong Zhou
Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios. It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples. Existing FOOD methods are subject to limited visual information, and often exhibit an ambiguous decision boundary between known and unknown classes. To address these limitations, we propose the first prompt-based few-shot open-set object detection framework, which exploits additional textual information and delves into constructing a robust decision boundary for unknown rejection. Specifically, as no available training data for unknown classes, we select pseudo-unknown samples with Attribution-Gradient based Pseudo-unknown Mining (AGPM), which leverages the discrepancy in attribution gradients to quantify uncertainty. Subsequently, we propose Conditional Evidence Decoupling (CED) to decouple and extract distinct knowledge from selected pseudo-unknown samples by eliminating opposing evidence. This optimization process can enhance the discrimination between known and unknown classes. To further regularize the model and form a robust decision boundary for unknown rejection, we introduce Abnormal Distribution Calibration (ADC) to calibrate the output probability distribution of local abnormal features in pseudo-unknown samples. Our method achieves superior performance over previous state-of-the-art approaches, improving the average recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. Our source code is available at https://gitee.com/VR_NAVE/ced-food.
少量开放集物体检测（FOOD）在许多开放世界场景中构成了一项挑战。它的目标是训练一个开放集检测器，在有限的训练样本下检测已知物体并拒绝未知物体。现有的FOOD方法受限于有限的视觉信息，并且在已知和未知类别之间往往表现出模糊的分界线。为了解决这些局限性，我们提出了基于提示的首个少量开放集物体检测框架，该框架利用额外的文本信息，并致力于构建用于未知拒绝的强大决策边界。具体来说，由于没有未知类别的可用训练数据，我们采用基于归因梯度的伪未知样本挖掘（AGPM）来选择伪未知样本，利用归因梯度的不一致性来量化不确定性。随后，我们提出了条件证据解耦（CED），通过消除对立证据，从选定的伪未知样本中解耦并提取独特的知识。这个优化过程可以增强已知和未知类别之间的辨别力。为了进一步规范模型并为未知的拒绝形成稳健的决策边界，我们引入了异常分布校准（ADC）来校准伪未知样本中局部异常特征的输出概率分布。我们的方法在VOC10-5-5数据集和VOC-COCO数据集的设定上均实现了超越先前最新方法的表现，未知类别的平均召回率分别提高了7.24%和1.38%。我们的源代码可在https://gitee.com/VR_NAVE/ced-food获取。
论文及项目相关链接
PDF Accepted to IJCAI 2025
Summary
本文介绍了面向开放世界场景中的Few-shot Open-set Object Detection（FOOD）挑战。针对现有FOOD方法受限于视觉信息、决策边界不明确的问题，提出了基于提示的少数开放集目标检测框架。该框架利用额外的文本信息，构建了一个用于未知拒绝的强大决策边界。通过挖掘伪未知样本、条件证据解耦和异常分布校准等技术，提高了模型对已知和未知类别的辨别能力，实现了对未知类的有效拒绝。
Key Takeaways
- Few-shot Open-set Object Detection (FOOD) 面临挑战：如何在有限训练样本下检测已知物体并拒绝未知物体。
- 现有FOOD方法受限于视觉信息，决策边界模糊。
- 提出基于提示的少数开放集目标检测框架，利用额外文本信息构建决策边界。
- 采用Attribution-Gradient based Pseudo-unknown Mining (AGPM) 挖掘伪未知样本。
- 提出Conditional Evidence Decoupling (CED) 解耦并提取伪未知样本中的独特知识。
- 通过Abnormal Distribution Calibration (ADC) 校准伪未知样本的局部异常特征输出概率分布，形成稳健的决策边界。
点此查看论文截图
