On the Exploration of Convolutional Fusion Networks for Visual Recognition

详细信息    查看全文

• 关键词：Multi ; scale deep representations ; Locally ; connected fusion module ; Transferring deep features ; Visual recognition
• 刊名：Lecture Notes in Computer Science
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：10132
• 期：1
• 页码：277-289
• 丛书名：MultiMedia Modeling
• ISBN：978-3-319-51811-4
• 卷排序：10132

文摘

Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules. Hence, we propose an efficient approach to fuse multi-scale deep representations, called convolutional fusion networks (CFN). Owing to using 1 \(\times \) 1 convolution and global average pooling, CFN can efficiently generate the side branches while adding few parameters. In addition, we present a locally-connected fusion module, which can learn adaptive weights for the side branches and form a discriminatively fused feature. CFN models trained on the CIFAR and ImageNet datasets demonstrate remarkable improvements over the plain CNNs. Furthermore, we generalize CFN to three new tasks, including scene recognition, fine-grained recognition and image retrieval. Our experiments show that it can obtain consistent improvements towards the transferring tasks.