论文标题
Adamixer：一个基于查询的对象检测器
AdaMixer: A Fast-Converging Query-Based Object Detector
论文作者
论文摘要
传统对象探测器采用图像中位置和尺度上扫描的密集范式。最近的基于查询的对象检测器通过用一组可学习的查询解码图像特征来打破了此惯例。但是，这种范式仍然患有缓慢的收敛性，有限的性能以及骨干和解码器之间额外网络的复杂性。在本文中，我们发现这些问题的关键是解码器施放查询以改变对象的适应性。因此，我们通过在两个方面改善基于查询的解码过程的适应性，提出了一个名为Adamixer的快速转换基于查询的检测器。首先，每个查询的样本都基于估计的偏移量在空间和尺度上的特征，这使Adamixer可以有效地进入对象的连贯区域。然后，在每个查询的指导下，我们用自适应MLP混合仪动态解码了这些采样功能。得益于这两个关键设计，Adamixer享受建筑简单性，而无需密集的注意编码器或明确的金字塔网络。在具有挑战性的MS Coco基准测试中，具有Resnet-50的Adamixer作为骨干，带有12个训练时期，在验证设置上最多可达45.0 AP，并在检测小物体时以及27.9 AP。借助较长的训练计划，Adamixer的Resnext-101-DCN和Swin-S达到49.5和51.3 AP。我们的工作阐明了基于查询的对象探测器的简单，准确且快速收敛的体系结构。该代码可从https://github.com/mcg-nju/adamixer提供
Traditional object detectors employ the dense paradigm of scanning over locations and scales in an image. The recent query-based object detectors break this convention by decoding image features with a set of learnable queries. However, this paradigm still suffers from slow convergence, limited performance, and design complexity of extra networks between backbone and decoder. In this paper, we find that the key to these issues is the adaptability of decoders for casting queries to varying objects. Accordingly, we propose a fast-converging query-based detector, named AdaMixer, by improving the adaptability of query-based decoding processes in two aspects. First, each query adaptively samples features over space and scales based on estimated offsets, which allows AdaMixer to efficiently attend to the coherent regions of objects. Then, we dynamically decode these sampled features with an adaptive MLP-Mixer under the guidance of each query. Thanks to these two critical designs, AdaMixer enjoys architectural simplicity without requiring dense attentional encoders or explicit pyramid networks. On the challenging MS COCO benchmark, AdaMixer with ResNet-50 as the backbone, with 12 training epochs, reaches up to 45.0 AP on the validation set along with 27.9 APs in detecting small objects. With the longer training scheme, AdaMixer with ResNeXt-101-DCN and Swin-S reaches 49.5 and 51.3 AP. Our work sheds light on a simple, accurate, and fast converging architecture for query-based object detectors. The code is made available at https://github.com/MCG-NJU/AdaMixer
