BriefGPT.xyz
Oct, 2016
用于对象识别的多实例学习卷积神经网络
Multiple Instance Learning Convolutional Neural Networks for Object Recognition
HTML
PDF
Miao Sun, Tony X. Han, Ming-Chang Liu, Ahmad Khodayari-Rostamabad
TL;DR
本文提出了一种名为多实例学习卷积神经网络(MILCNN)的弱监督卷积神经网络框架,用于解决深度网络训练数据不足的问题, 将MILCNN框架应用于目标识别, 并在三个基准数据集(CIFAR10、CIFAR100和ILSVRC2015)上报告了最新成果。
Abstract
convolutional neural networks
(CNN) have demon- strated its successful applications in computer vision, speech recognition, and natural language processing. For object recog- nition, CNNs might be limited by its strict
→