IOR：反向物体回放用于增量物体检测
IOR: Inversed Objects Replay for Incremental Object Detection
AI总结：
本文提出IOR方法，通过反向检测器生成旧类样本，减少冗余生成和存储，提升增量物体检测性能。
摘要：
现有的增量物体检测（IOD）方法在逐步检测现实世界中新物体时部分缓解了灾难性遗忘问题。然而，许多这些方法依赖于假设：在增量数据中，未标记的旧类物体可能与标记的新类物体同时出现。当未标记的旧类物体缺失时，现有方法的性能往往会下降。通过生成旧类样本可以缓解这种缺失，但会带来高成本。本文认为，以前基于生成的IOD存在冗余，这体现在生成模型的使用上，需要额外训练和存储，以及生成样本的过度生产，其中许多样本对性能提升没有显著贡献。为了消除冗余，我们提出了反向物体回放（IOR）。具体来说，我们通过反向原始检测器生成旧类样本，从而消除了训练和存储额外生成模型的必要性。我们提出增强回放，以重用生成样本中的物体，减少冗余生成。此外，我们提出高价值知识蒸馏，专注于被背景淹没的旧类物体的位置，将知识转移到增量检测器中。在MS COCO 2017上进行的大量实验表明，我们的方法在缺少旧类物体的情况下能够有效提高IOD场景的检测性能。代码可在https://github.com/JiaJia075/IOR上获得。
英文摘要：
Existing Incremental Object Detection (IOD) methods partially alleviate catastrophic forgetting when incrementally detecting new objects in real-world scenarios. However, many of these methods rely on the assumption that unlabeled old-class objects may co-occur with labeled new-class objects in the incremental data. When unlabeled old-class objects are absent, the performance of existing methods tends to degrade. The absence can be mitigated by generating old-class samples, but it incurs high costs. This paper argues that previous generation-based IOD suffers from redundancy, both in the use of generative models, which require additional training and storage, and in the overproduction of generated samples, many of which do not contribute significantly to performance improvements. To eliminate the redundancy, we propose Inversed Objects Replay (IOR). Specifically, we generate old-class samples by inversing the original detectors, thus eliminating the necessity of training and storing additional generative models. We propose augmented replay to reuse the objects in generated samples, reducing redundant generations. Moreover, we propose high-value knowledge distillation focusing on the positions of old-class objects overwhelmed by the background, which transfers the knowledge to the incremental detector. Extensive experiments conducted on MS COCO 2017 demonstrate that our method can efficiently improve detection performance in IOD scenarios with the absence of old-class objects. The code is available at https://github.com/JiaJia075/IOR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
