计算机技术与发展2024，Vol.34Issue(1)：37-43,7.DOI:10.3969/j.issn.1673-629X.2024.01.006
基于EfficientNet的无锚框目标检测模型
An Anchor-free Object Detection Model Based on EfficientNet
摘要
Abstract
Object detection is one of the hot research areas in computer vision,which includes two tasks:classification and location.Due to the two common problems appearing in one-stage object detector:extreme imbalance between positive/negative samples during training and anchors pre-defined deeply depending on manual settings,an anchor-free efficientnet-based object detector(AEOD)is pro-posed.AEOD first selects out the feature points that fall in the target box,then calculates the cost matrix based on values predicted by these feature points,finally assigns the positive/negative samples to the target dynamically according to the cost matrix during the training.Therefore,the number of positive/negative samples is balanced to enhance the performance of the model.AEOD directly predicts location and shape of the object through the feature points in the feature maps.As a result,not only the step of pre-defining anchors can be skipped,but also the number of objects that successfully detected increases.In addition,the scalable backbone(EfficientNet)improves the generalization ability of AEOD,it can receive multi-scale input.AEOD achieves the highest 91.3%mAP on PASCAL VOC07+12 at speed of 32.1 FPS,showing a significant improvement compared to other modern models.关键词
深度学习/计算机视觉/目标检测/正负样本分配算法/无锚框Key words
deep learning/computer vision/object detection/positive/negative samples assignment algorithm/anchor-free分类
信息技术与安全科学引用本文复制引用
卜子渝,杨哲,刘纯平..基于EfficientNet的无锚框目标检测模型[J].计算机技术与发展,2024,34(1):37-43,7.基金项目
国家自然科学基金资助项目(62002253) （62002253）
江苏省高校自然科学基金资助项目(19KJA230001) （19KJA230001）
