Convolutional Neural Networks (CNN) have dominated the field of detection ever since the success of AlexNet in ImageNet classification [12]. With the sweeping reform of Transformers [27] in natural language processing, Carion et al. [2] introduce the Transformer-based detection method, i.e., DETR. However, due to the quadratic complexity in the self-attention mechanism in the Transformer, DETR is never able to incorporate multi-scale features as performed in existing CNN-based detectors, leading to inferior results in small object detection. To mitigate this issue and further improve performance of DETR, in this work, we investigate different methods to incorporate multi-scale features and find that a Bi-directional Feature Pyramid (BiFPN) works best with DETR in further raising the detection precision. With this discovery, we propose DETR++, a new architecture that improves detection results by 1.9% AP on MS COCO 2017, 11.5% AP on RICO icon detection, and 9.1% AP on RICO layout extraction over existing baselines.
翻译:自AlexNet成功在图像网络分类[12]以来,革命神经网络(CNN)一直主导着探测领域。随着自然语言处理中变换器的大规模改革[27],Carion等人[2]引入了以变换器为基础的探测方法,即DETR。然而,由于变换器中自留机制的二次复杂性,DETR永远无法纳入现有CNN探测器中实施的多尺度特征,导致小物体探测结果低。为了缓解这一问题并进一步提高DETR的性能,我们在这项工作中调查采用不同方法,以纳入多尺度特征,发现双向地貌图像仪(BIFPN)与DETR在进一步提高探测精确度方面最有效。我们提出DETR++,这是一个新的结构,通过1.9% AP改进现有基线的MS CO 2017的探测结果,11.5% AP关于RICO图标探测的探测,9.1% AP关于RICO的布局。