English

Dual Skipping Networks

Computer Vision and Pattern Recognition 2018-05-29 v3 Artificial Intelligence

Abstract

Inspired by the recent neuroscience studies on the left-right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object categorization. Such a network has two branches to simultaneously deal with both coarse and fine-grained classification tasks. Specifically, we propose a layer-skipping mechanism that learns a gating network to predict which layers to skip in the testing stage. This layer-skipping mechanism endows the network with good flexibility and capability in practice. Evaluations are conducted on several widely used coarse-to-fine object categorization benchmarks, and promising results are achieved by our proposed network model.

Keywords

Cite

@article{arxiv.1710.10386,
  title  = {Dual Skipping Networks},
  author = {Changmao Cheng and Yanwei Fu and Yu-Gang Jiang and Wei Liu and Wenlian Lu and Jianfeng Feng and Xiangyang Xue},
  journal= {arXiv preprint arXiv:1710.10386},
  year   = {2018}
}

Comments

CVPR 2018 (poster); fix typo

R2 v1 2026-06-22T22:28:17.694Z