Neural network feature map quantization method and device
A neural network-based signal processing method and device according to the present invention generates a feature map by means of a multilayer neural network comprising a plurality of neural networks, and performs quantization for the feature map, the quantization performed on the basis of the structure of the multilayer neural network or the attribute of the feature map.
1. A neural network based video signal processing method, the method comprising:
generating a feature map by using multiple neural networks including a plurality of neural networks; and
performing quantization on the feature map,
wherein the quantization is performed based on an attribute of the feature map or a structure of the multiple neural networks, and
wherein a structure of the multiple neural networks includes at least one of whether the multiple neural networks are connected in series, whether the multiple neural networks are connected in parallel, whether the multiple neural networks are connected in series and in parallel, or a type of a layer adjacent to a current layer that the feature map is generated.
2. The method according to claim 1 ,
wherein the attribute of the feature map includes a distribution type of sample values in the feature map, and
wherein the quantization is performed by a quantization method mapped to the distribution type.
3. The method according to claim 2 ,
wherein the distribution type includes at least one of an uniform distribution, a Gaussian distribution or a Laplace distribution.
4. The method according to claim 2 , wherein performing the quantization comprises,
performing normalization on sample values in the feature map by a normalization method mapped to the distribution type.
5. The method according to claim 1 ,
wherein the quantization is performed by a quantization method mapped to the type of the adjacent layer, and
wherein the type of the layer includes at least one of a batch normalization layer or a summation layer.
6. The method according to claim 1 ,
wherein classifying the feature map into a plurality of classes is further included, and
wherein the attribute of the feature map includes a class of the feature map.
7. The method according to claim 6 ,
wherein the feature map includes a plurality of channels, and
wherein the feature map is classified into the plurality of classes including at least one channel based on a similarity between the plurality of channels.
8. The method according to claim 6 ,
wherein the feature map is spatially classified based on a spatial similarity of an input image.
9. A neural network based video signal processing device, the device comprising:
a processor which controls the video signal processing device; and
a memory which is combined with the processor and stores data,
wherein the processor is configured to:
generate a feature map by using multiple neural networks including a plurality of neural networks, and
perform quantization on the feature map,
wherein the quantization is performed based on an attribute of the feature map or a structure of the multiple neural networks, and
wherein a structure of the multiple neural networks includes at least one of whether the multiple neural networks are connected in series, whether the multiple neural networks are connected in parallel, whether the multiple neural networks are connected in series and in parallel, or a type of a layer adjacent to a current layer that the feature map is generated.