Convolutional-neural-network-based classifier and classifying method and training methods for the same

1. A method for training the convolutional-neural-network-based classifier, which comprises a plurality of feature map layers, comprising:

dividing at least one feature map in at least one of the plurality of the feature map layers into a plurality of regions;

performing forward propagation by inputting a training sample with a known flag into the convolutional-neural-network-based classifier to obtain an output result, during the forward propagation, each of the convolutional templates, which correspond to the plurality of regions respectively, is used for obtaining a response value of a neuron in the corresponding region;

performing back propagation according to the difference between the output result and the known flag to correct parameters of the convolutional-neural-network-based classifier comprising the weights in the convolutional template; and

repeating the above steps until a predetermined condition is met,

wherein, one of schemes of the dividing are different for different feature maps and schemes of the dividing are different for different training samples.

2. The method according to claim 1 , wherein the training sample is an image, the step of dividing at least one feature map in at least one of the plurality of the feature map layers into a plurality of regions comprising:

dividing the image into a plurality of images regions, which correspond to the plurality of regions respectively, according to a fixed scheme respectively, wherein the fixed scheme is determined based on general features of the training sample.

3. The method according to claim 1 , wherein the training sample is an image, the step of dividing at least one feature map in at least one of the plurality of the feature map layers into a plurality of regions comprising:

dividing each image into a plurality of image regions, which correspond to the plurality of regions respectively, based on the personal features of each the image respectively.

4. The method according to claim 3 , wherein the step of dividing at least one feature map in at least one of the plurality of the feature map layers into a plurality of regions comprises:

dividing the at least one feature map into the plurality of regions based on a pixel distribution of the image.

5. The method according to claim 4 , wherein the step of dividing at least one feature map in at least one of the plurality of the feature map layers into a plurality of regions comprises:

dividing the at least one feature map into the plurality of regions based on a quantity distribution or a density distribution of foreground pixels of a binary image of the image.

6. The method of claim 1 , wherein the step of dividing at least one feature map in at least one of the plurality of the feature map layers into a plurality of regions comprises:

dividing the at least one feature map into the plurality of regions based on the structure of the image.

7. The method of claim 1 , wherein the step that each of the convolutional templates, which correspond to the plurality of regions respectively, is used for obtaining a response value of a neuron in the corresponding region comprises:

using an activation function which is configured to acquire a positive response value, to obtain the response value of the neuron in the corresponding region.

8. The method of claim 7 , wherein the activation function is configured to take an absolute value for a negative convolutional result or to convert a negative convolutional result to a positive small value.