5,337
edits
Visual Learning and Recognition: Difference between revisions
→Single Stage Multibox Detector (SSD)
| Line 437: | Line 437: | ||
===Single Stage Multibox Detector (SSD)=== | ===Single Stage Multibox Detector (SSD)=== | ||
Liu ''et al'' (2016) propose SSD: Single Shot MultiBox Detector. | |||
The idea is that they train a CNN to do object detection over the entire image. | |||
The CNN outputs multiple feature maps for each of the categories, each with different aspect ratios and scales. | |||
Pixels of the feature maps are ''default boxes'', representing a default bounding box. | |||
Each feature map gives candidate results which are filtered using non-maximum suppression. | |||
Different scales are achieved by extracting feature maps from intermediate layers of the network. | |||
The aspect ratio of each default box does not actually correspond to the receptive field associated with the feature pixel. | |||
During training, all ''default boxes'' with jaccard overlap >0.5 with the ground truth are matched. | |||
They also apply hard negative mining and data augmentation. | |||
===YOLO=== | ===YOLO=== | ||