| CPC G06F 18/217 (2023.01) [G06F 18/213 (2023.01); G06N 3/08 (2013.01); G06V 10/462 (2022.01)] | 17 Claims |
|
1. A computing processor-based method of generating an aggregate saliency map using a convolutional neural network model, wherein the convolutional neural network model includes multiple encoding layers, the computing processor-based method comprising:
receiving convolutional activation maps of the convolutional neural network model into a saliency map generator, the convolutional activation maps being generated by the convolutional neural network model while computing one or more prediction scores based on unlabeled input data, each convolutional activation map corresponding to one of the multiple encoding layers;
generating, in the saliency map generator, a layer-dependent saliency map for each encoding layer of the unlabeled input data, each layer-dependent saliency map being based on a summation of element-wise products of the convolutional activation maps and their corresponding gradients;
combining the layer-dependent saliency maps into the aggregate saliency map indicating relative contributions of individual components of the unlabeled input data to the one or more prediction scores computed by the convolutional neural network model on the unlabeled input data; and
refining the convolutional neural network model based on the aggregate saliency map for the unlabeled input data.
|