Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to catastrophic forgetting, which is often addressed by techniques such as knowledge distillation (KD) and exemplar replay (ER). However, KD and ER do not work well if applied directly to state-of-the-art transformer-based object detectors such as Deformable DETR and UP-DETR. In this paper, we solve these issues by proposing a ContinuaL DEtection TRansformer (CL-DETR), a new method for transformer-based IOD which enables effective usage of KD and ER in this context. First, we introduce a Detector Knowledge Distillation (DKD) loss, focusing on the most informative and reliable predictions from old versions of the model, ignoring redundant background predictions, and ensuring compatibility with the available ground-truth labels. We also improve ER by proposing a calibration strategy to preserve the label distribution of the training set, therefore better matching training and testing statistics. We conduct extensive experiments on COCO 2017 and demonstrate that CL-DETR achieves state-of-the-art results in the IOD setting.

翻译：增量目标检测（IOD）旨在分阶段训练目标检测器，每个阶段包含对新目标类别的标注。与其他增量设置类似，IOD存在灾难性遗忘问题，通常通过知识蒸馏（KD）和样本回放（ER）等技术解决。然而，直接将KD和ER应用于基于Transformer的先进目标检测器（如Deformable DETR和UP-DETR）时效果不佳。本文提出持续检测Transformer（CL-DETR）解决上述问题，这是一种基于Transformer的IOD新方法，可在该背景下有效利用KD和ER。首先，我们引入检测器知识蒸馏（DKD）损失，聚焦于旧模型版本中信息量最大且最可靠的预测，忽略冗余背景预测，并确保与可用真实标签的兼容性。同时，我们通过提出校准策略改进ER，以保留训练集的标签分布，从而更好地匹配训练与测试统计特性。在COCO 2017数据集上的大量实验表明，CL-DETR在IOD设置中达到了最先进的性能。