摘要： Abstract The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decod 阅读全文

摘要： ABSTRACT As a data-driven method, the performance of deep convolutional neural networks (CNN) relies heavily on training data. The prediction results 阅读全文

摘要： ESRGAN是在SRGAN基础上进行增强的网络, 在2018年的比赛中获得了冠军 Introduction 介绍了基于PSNR指标获得的超分辨图像其结果会较为平滑，且与人们的主观有较大的差别 作者针对SRGAN提出了3个改进的点 第一点: 使用了RDDB网络结构, 这种层叠式的网络结构更容易表达效果 阅读全文

摘要： Abstract In this paper, we introduce the problem of simultaneously detecting multiple photographic defects. We aim at detecting the existence, severit 阅读全文

摘要： Abstract Anomaly detection refers to the task of finding unusual instances that stand out from the normal data. In several applications, these outlier 阅读全文

摘要： Abstract We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous da 阅读全文

摘要： 这篇文章不管是网络结构还是文章中提到的亮点基本都是复用了<End-to-end training of a two-stage neural network for defect detection> 唯一的不同点就是针对混合监督，针对其中只有正负标签，没有分割标签的数据，损失函数只是用分类损失函数 阅读全文

摘要： 这篇文章相比于Segmentation-based deep- ˇ learning approach for surface-defect detection.这篇文章，首先他们都是一个作者写的，其次网络的架构也是非常接近的 为了保证小细节被保留下来，这里使用的是max-pool2x2，而不是使用 阅读全文

摘要： Abstract Detection identififies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of pote 阅读全文

摘要： ░ YOLOX: Exceeding YOLO Series in 2021 1. Inclusion 介于yoloV4和yoloV5在基于anchor的pipeline上的过度优化，因此使用Yolov3作为我们的基础网络 Considering YOLOv4 and YOLOv5 may be a 阅读全文