SSD

发表于 更新于 分类于 阅读次数： 本文字数： 152 阅读时长 ≈ 1 分钟

SSD: Single Shot MultiBox Detector[1]

作者是 Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg，分别来自UNC Chapel Hill，Zoox Inc, Google, UMichigan。论文引用[1]:Liu, W. et al. “SSD: Single Shot MultiBox Detector.” European Conference on Computer Vision (2015).

Key Words

  • discretize output space of bboxes into a set of default boxes over different aspect ratios and scales.
  • combines predictions from multiple feature maps with different resolutions to handle objects of various sizes
  • multi-scale conv bbox outputs attached to multiple feataure maps at the top of the network #### 总结 以下“我们”指代作者
  1. match each GT box to defacult box with the best jaccard overlap(as in MultiBox), match default boxes to any GT with jaccard overlap higher than a threshold(0.5).
SSD vs YOLO