Timezone: »

Dual Path Networks
Yunpeng Chen · Jianan Li · Huaxin Xiao · Xiaojie Jin · Shuicheng Yan · Jiashi Feng

Wed Dec 06 03:20 PM -- 03:25 PM (PST) @ Hall A

In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally. By revealing the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, we find that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations. To enjoy the benefits from both path topologies, our proposed Dual Path Network shares common features while maintaining the flexibility to explore new features through dual path architectures. Extensive experiments on three benchmark datasets, ImagNet-1k, Places365 and PASCAL VOC, clearly demonstrate superior performance of the proposed DPN over state-of-the-arts. In particular, on the ImagNet-1k dataset, a shallow DPN surpasses the best ResNeXt-101(64x4d) with 26% smaller model size, 25% less computational cost and 8% lower memory consumption, and a deeper DPN achieves the state-of-the-art single model performance with more than 3 times faster training speed. Experiments on the Places365 large-scale scene dataset, PASCAL VOC detection dataset, and PASCAL VOC segmentation dataset also demonstrate its consistently better performance than DenseNet, ResNet and the latest ResNeXt model over various applications.

Author Information

Yunpeng Chen (National University of Singapore)
Jianan Li (Beijing Institute of Technology)
Huaxin Xiao (NUDT)
Xiaojie Jin (National University of Singapore & Snap Research)
Shuicheng Yan (Qihoo 360 AI Institute)
Jiashi Feng (National University of Singapore)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors