2020/09/29 by Heng Zhang, Elisa Fromont, Zhang, Heng +7
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #cs.CV
paper · pdf · doi:10.48550/arxiv.2009.14085
Accepted by ACCV 2020
arxiv created 2020/09/29 · openalex publication_date 2020/09/29 · arxiv updated 2020/09/30 · openalex created_date 2020/10/08 · openalex updated_date 2026/07/28
Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects. In this paper, we question this use of IoU and propose a new anchor matching criterion guided, during the training phase, by the optimization of both the localization and the classification tasks: the predictions related to one task are used to dynamically assign sample anchors and improve the model on the other task, and vice versa. Despite the simplicity of the proposed method, our experiments with different state-of-the-art deep learning architectures on PASCAL VOC and MS COCO datasets demonstrate the effectiveness and generality of our Mutual Guidance strategy.