通过共享属性缓解增量检测中的遗忘问题
CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection
- 用大模型生成候选属性，动态选择关键共享特征
- 在COCO上实现当前最优的增量检测效果
- 适合需要持续学习新类别的视觉系统
增量目标检测面临灾难性遗忘问题，主要由背景类别在不同任务间重叠引起。本文提出类无关共享属性基（CASA），促使模型学习跨增量类别的通用属性。方法利用大语言模型生成候选文本属性，根据当前训练数据筛选相关属性，并记录其重要性至分配矩阵。后续任务中，保留已有属性并从剩余候选中选择新属性，兼顾知识保留与适应能力。在COCO数据集上的大量实验表明，该方法达到当前最优性能。
原文摘要 · Abstract (English)
Incremental object detection is fundamentally challenged by catastrophic forgetting. A major factor contributing to this issue is background shift, where background categories in sequential tasks may overlap with either previously learned or future unseen classes. To address this, we propose a novel method called Class-Agnostic Shared Attribute Base (CASA) that encourages the model to learn category-agnostic attributes shared across incremental classes. Our approach leverages an LLM to generate candidate textual attributes, selects the most relevant ones based on the current training data, and records their importance in an assignment matrix. For subsequent tasks, the retained attributes are frozen, and new attributes are selected from the remaining candidates, ensuring both knowledge retention and adaptability. Extensive experiments on the COCO dataset demonstrate the state-of-the-art performance of our method.
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。