Timezone: »

 
Poster
Dual-stream Network for Visual Recognition
Mingyuan Mao · peng gao · Renrui Zhang · Honghui Zheng · Teli Ma · Yan Peng · Errui Ding · Baochang Zhang · Shumin Han

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @
in Poster Session 3 »

Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images. In this paper, we present a generic Dual-stream Network (DS-Net) to fully explore the representation capacity of local and global pattern features for image classification. Our DS-Net can simultaneously calculate fine-grained and integrated features and efficiently fuse them. Specifically, we propose an Intra-scale Propagation module to process two different resolutions in each block and an Inter-Scale Alignment module to perform information interaction across features at dual scales. Besides, we also design a Dual-stream FPN (DS-FPN) to further enhance contextual information for downstream dense predictions. Without bells and whistles, the proposed DS-Net outperforms DeiT-Small by 2.4\% in terms of top-1 accuracy on ImageNet-1k and achieves state-of-the-art performance over other Vision Transformers and ResNets. For object detection and instance segmentation, DS-Net-Small respectively outperforms ResNet-50 by 6.4\% and 5.5 \% in terms of mAP on MSCOCO 2017, and surpasses the previous state-of-the-art scheme, which significantly demonstrates its potential to be a general backbone in vision tasks. The code will be released soon.

Keywords: Machine Learning · Transformers · Vision

Author Information

Mingyuan Mao (Beihang University)
peng gao (allen institute for artificial intelligence ai2)
Renrui Zhang (Peking University)
Honghui Zheng (Beijing University of Post and Telecommunication)
Teli Ma
Yan Peng (National University of Defense Technology)
Errui Ding (Baidu Inc.)
Baochang Zhang (Beihang University)
Shumin Han (Baidu)

More from the Same Authors