Despite previous DETR-like methods having performed successfully in generic
object detection, tiny object detection is still a challenging task for them
since the positional information of object queries is not customized for
detecting tiny objects, whose scale is extraordinarily smaller than general
objects. Also, DETR-like methods using a fixed number of queries make them
unsuitable for aerial datasets, which only contain tiny objects, and the
numbers of instances are imbalanced between different images. Thus, we present
a simple yet effective model, named DQ-DETR, which consists of three different
components: categorical counting module, counting-guided feature enhancement,
and dynamic query selection to solve the above-mentioned problems. DQ-DETR uses
the prediction and density maps from the categorical counting module to
dynamically adjust the number of object queries and improve the positional
information of queries. Our model DQ-DETR outperforms previous CNN-based and
DETR-like methods, achieving state-of-the-art mAP 30.2% on the AI-TOD-V2
dataset, which mostly consists of tiny objects.

我们提出了一种名为 DQ-DETR 的简单而有效的模型，其中包括三个不同的组件：分类计数模块、计数引导的特征增强和动态查询选择，以解决 DET-R 类型方法在检测微小对象方面的挑战。DQ-DETR 使用分类计数模块的预测和密度图动态调整物体查询的数量，并改善查询的位置信息。我们的模型 DQ-DETR 在以微小对象为主的 AI-TOD-V2 数据集上实现了 30.2% 的最优 mAP，优于以前基于 CNN 和 DET-R 类型方法的性能。

DQ-DETR：用于微小物体检测的具有动态查询的 DETR

DQ-DETR: DETR with Dynamic Query for Tiny Object Detection

DETR-like methods have significantly increased detection performance in an
end-to-end manner. The mainstream two-stage frameworks of them perform dense
self-attention and select a fraction of queries for sparse cross-attention,
which is proven effective for improving performance but also introduces a heavy
computational burden and high dependence on stable query selection. This paper
demonstrates that suboptimal two-stage selection strategies result in scale
bias and redundancy due to the mismatch between selected queries and objects in
two-stage initialization. To address these issues, we propose hierarchical
salience filtering refinement, which performs transformer encoding only on
filtered discriminative queries, for a better trade-off between computational
efficiency and precision. The filtering process overcomes scale bias through a
novel scale-independent salience supervision. To compensate for the semantic
misalignment among queries, we introduce elaborate query refinement modules for
stable two-stage initialization. Based on above improvements, the proposed
Salience DETR achieves significant improvements of +4.0% AP, +0.2% AP, +4.4% AP
on three challenging task-specific detection datasets, as well as 49.2% AP on
COCO 2017 with less FLOPs. The code is available at
this https URL

通过引入分层显著性筛选细化和稳定的两阶段初始化查询模块，该研究论文在 DETR 类方法中取得了显著的性能提升，克服了规模偏差和语义不匹配的问题，并在多个任务特定的检测数据集上实现了 4.0% ~ 4.4% 的平均准确率（AP）提高以及在 COCO 2017 数据集上实现了 49.2% 的 AP 提高，并且使用更少的 FLOPs 达到了更高的计算效率。