5,343
edits
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. |