Analyzing The Performance Of Multilayer Neural Networks For Object Recognition
COMPUTER VISION - ECCV 2014, PT VII(2014)
摘要
In the last two years, convolutional neural networks (CNNs) have achieved an impressive suite of results on standard recognition datasets and tasks. CNN-based features seem poised to quickly replace engineered representations, such as SIFT and HOG. However, compared to SIFT and HOG, we understand much less about the nature of the features learned by large CNNs. In this paper, we experimentally probe several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems.
更多查看译文
关键词
convolutional neural networks, object recognition, empirical analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络