VGGNet激活的分类混合模型
Categorical Mixture Models on VGGNet activations
摘要：
在这个项目中，我使用了无监督学习技术，以便将一组yelp餐厅照片聚类到有意义的主题下。为了做到这一点，我从流行的VGGNet卷积神经网络的预训练实现中提取层激活。首先，我探索使用LDA，将卷积层的激活作为特征。其次，我探索使用在ImageNet上训练的VGGNet的对象识别能力，以便从照片中提取有意义的对象，然后执行LDA将照片分组到主题原型下。我发现第二种方法找到了有意义的原型，这些原型符合人类对餐馆、食物和饮料等照片主题的直觉。此外，这些聚类与实际的Yelp照片标签很好地对齐。
英文摘要：
In this project, I use unsupervised learning techniques in order to cluster a set of yelp restaurant photos under meaningful topics. In order to do this, I extract layer activations from a pre-trained implementation of the popular VGGNet convolutional neural network. First, I explore using LDA with the activations of convolutional layers as features. Secondly, I explore using the object-recognition powers of VGGNet trained on ImageNet in order to extract meaningful objects from the photos, and then perform LDA to group the photos under topic-archetypes. I find that this second approach finds meaningful archetypes, which match the human intuition for photo topics such as restaurant, food, and drinks. Furthermore, these clusters align well and distinctly with the actual yelp photo labels.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
