Back to results
US 2025/0220182 A1Published application
Method and device for compressing feature tensor on basis of neural network
AssigneeIntellectual Discovery Co., Ltd.
InventorsYongjo AHN, Jongseok LEE
Life of this patent
Estimating the term…
Abstract
A method and a device for processing an image on the basis of a neural network, according to an embodiment of the present invention, can acquire a feature tensor from an input image by using a first neural network including a plurality of neural network layers, acquire a quantized feature tensor by quantizing the acquired feature tensor on the basis of the quantization size, and generate a bitstream by performing entropy encoding on the quantized feature tensor.
Claims15
A neural network-based image processing method, comprising:
- acquiring a feature tensor from an input image by using a first neural network including a plurality of neural network layers;
- acquiring a quantized feature tensor by quantizing the acquired feature tensor based on a quantization size;
- and
- generating a bitstream by performing entropy encoding on the quantized feature tensor,
- wherein the quantization size is adaptively derived based on predefined encoding information.
2 more elements
A neural network-based image processing device, comprising:
- a processor configured to control the image processing device;
- and
- a memory connected to the processor, the memory being configured to store data, wherein the processor is configured to:
- acquire a feature tensor from an input image by using a first neural network including a plurality of neural network layers,
- acquire a quantized feature tensor by quantizing the acquired feature tensor based on a quantization size,
- generate a bitstream by performing entropy encoding on the quantized feature tensor,
- wherein the quantization size is adaptively derived based on predefined encoding information.
4 more elements
Dependencies are inferred from the claim text.