Abstract Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), ie.,
detecting multiple and single instances with bounding boxes in an image using image-level …

Abstract Class Activation Map (CAM) is one of the most popular approaches to visually
explain the convolutional neural networks (CNNs). To obtain fine-grained saliency maps …

With the widespread use of UAVs in military struggles, how to take effective measures to
achieve the detection of UAV targets has become a focus of attention in various countries …

In weakly supervised object localization (WSOL), objects are localized using image-level
labels only. Most previous WSOL methods erase the most discriminative region using a fixed …

随着卷积神经网络(Convolutional Neural Network, CNN) 的不断发展, 目标检测作为计算机
视觉中最基本的技术, 已取得了令人瞩目的进展. 介绍了强监督目标检测算法对数据集标注精度 …

The weakly supervised object localization (WSOL) has always been a very challenging
research subject in the field of computer vision, which aims to predict the localization of …

Channel and spatial attention mechanisms have proven to provide an evident performance
boost of deep convolution neural networks. Most existing methods focus on one or run them …

Weakly-supervised object detection (WSOD) has attracted many people's attention because
it can reduce labor and time-consuming, and some bias or errors caused by the subjectivity …

In this thesis, we propose two models for weakly supervised object localization (WSOL).
Many existing WSOL models have various burdens of learning, eg, the nonnegligible cost of …