5,343
edits
Visual Learning and Recognition: Difference between revisions
Visual Learning and Recognition (view source)
Revision as of 15:38, 28 October 2020
, 28 October 2020→ION: Inside-Outside Network
| Line 650: | Line 650: | ||
* The outputs of each RNN are concatenated, yielding an image with the same shape. | * The outputs of each RNN are concatenated, yielding an image with the same shape. | ||
For each RoI identified using object proposals: | |||
* Do L2 normalization of the features at different layers (Conv3, conv4, conv5, and context features) | * Do L2 normalization of the features at different layers (Conv3, conv4, conv5, and context features) | ||
* Concatenate features to a single feature image. | * Concatenate features to a single feature image. | ||