StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection

  title={StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection},
  author={Sanghyun Woo and Soonmin Hwang and In-So Kweon},
  journal={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
One-stage object detectors such as SSD or YOLO already have shown promising accuracy with small memory footprint and fast speed. However, it is widely recognized that one-stage detectors have difficulty in detecting small objects while they are competitive with two-stage methods on large objects. In this paper, we investigate how to alleviate this problem starting from the SSD framework. Due to their pyramidal design, the lower layer that is responsible for small objects lacks strong semantics… CONTINUE READING



Citations per Year

Citation Velocity: 8

Averaging 8 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.