Teaching Compositionality to CNNs

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2017)

引用 72|浏览82
暂无评分
摘要
Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting and training CNNs so that their learned features are compositional. It encourages networks to form representations that disentangle objects from their surroundings and from each other, thereby promoting better generalization. Our method is agnostic to the specific details of the underlying CNN to which it is applied and can in principle be used with any CNN. As we show in our experiments, the learned representations lead to feature activations that are more localized and improve performance over non-compositional baselines in object recognition tasks.
更多
查看译文
关键词
CNNs,convolutional neural networks,computer vision,human-level performance,application-specific loss functions,noncompositional baselines,object recognition tasks,representation learning,compositionality teaching,compositional learned features,object representations
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要