This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two limitations: lack of training emphasis and cascading errors from decoding sequence. We design and present Selective Query Recollection (SQR), a simple and effective training strategy for query-based object detectors. It cumulatively collects intermediate queries as decoding stages go deeper and selectively forwards the queries to the downstream stages aside from the sequential structure. Such-wise, SQR places training emphasis on later stages and allows later stages to work with intermediate queries from earlier stages directly. SQR can be easily plugged into various query-based object detectors and significantly enhances their performance while leaving the inference pipeline unchanged. As a result, we apply SQR on Adamixer, DAB-DETR, and Deformable-DETR across various settings (backbone, number of queries, schedule) and consistently brings 1.4-2.8 AP improvement.
翻译:本文调查了一个基于查询的物体探测器在最后解码阶段错误预测,同时在中间阶段正确预测的现象。我们审查了培训过程,并将被忽视的现象归结为两个局限性:缺乏培训重点和解码序列中的分层错误。我们设计并展示了基于查询的物体探测器简单有效的培训战略“选择性查询回忆”(SQR),这是对基于查询的物体探测器的一种简单有效的培训战略。它累积收集了作为解码阶段的中间查询,将解码阶段更深,有选择地将查询推进到下游阶段,而不在顺序结构之外。这样,SQR将培训重点放在后期,允许后期阶段直接与早期的中间查询一起工作。SQR可以很容易地插入各种基于查询的物体探测器,极大地提高它们的性能,同时使推断管道保持不变。结果,我们在不同环境(背骨、查询次数、时间表)中应用SQR(SQR)、DAB-DETR)和变形-DETR,并不断实现1.4-2.8 AP的改进。