KR-20260063059-A - Method and system for data augmentation for object-centric explainable model learning

KR20260063059AKR 20260063059 AKR20260063059 AKR 20260063059AKR-20260063059-A

Abstract

A method for augmenting object-centered explainable model learning data includes: a step in which a system acquires image data for object detection; a step in which the system applies the acquired image data to an object detection model to extract an object region (I ROI ); and a step in which the system generates augmented image data (I H ) by applying a Hann window function to the object region (I ROI ). By doing so, a visual intelligence model with applied explainable technology can be induced to learn in an object-centered manner.

Inventors

김귀식
조충상

Assignees

한국전자기술연구원

Dates

Publication Date: 20260507
Application Date: 20241030

Claims (12)

The system acquires image data for object detection; The system applies acquired image data to an object detection model to extract an object region (I ROI ); and An object-oriented explainable model learning data augmentation method comprising the step of the system generating augmented image data (I H ) by applying a Hann window function to an object region (I ROI ).
In claim 1, Hann window functions are, An object-centered explainable model learning data augmentation method characterized by excluding the outer region formed in a curved shape along the border and setting only the central region to be reinforced.
In claim 2, Hann window functions are, An object-centered explainable model learning data augmentation method characterized by excluding an outer region formed in a curved shape along the border and reinforcing only the central region, wherein the applied image is set to have a value within a preset error range of 1 or 1 in the central region and a value within a preset error range of 0 or 0 in the outer region formed in a curved shape along the border.
In claim 3, The Hann window function (h(n)) is, An object-oriented explainable model learning data augmentation method characterized by being calculated through the following Formula 1. (Formula 1)
In claim 1, An object-centered explainable model learning data augmentation method characterized by further including the step of setting weights for scaling the center region in the Hann window function before the system applies the Hann window function to the object region (I ROI ).
In claim 5, The step of setting weight(s) for scaling the central region is, An object-oriented explainable model training data augmentation method characterized by setting weights by referring to Formula 2 below when the basic Hann window function is h. (Equation 2)
In claim 6, The weight(s) for scaling the central region are, An object-centered explainable model learning data augmentation method characterized by the fact that the scale is adjusted relatively smoothly as the value becomes relatively smaller.
In claim 1, Augmented image data (I H ) is, An object-centered explainable model training data augmentation method characterized by being usable as training data or input data for a synthetic face recognition model to which explainable technology is applied.
In claim 1, The system further includes the step of generating a training dataset based on augmented image data (I H ), and The training dataset is, An object-centered explainable model learning data augmentation method characterized by including multiple augmented image data (I H ) generated by applying different weights(s) to the same object region (I ROI ).
A communication unit for acquiring image data for object detection; and An object-oriented explainable model learning data augmentation system comprising: a processor that applies acquired image data to an object detection model to extract an object region (I ROI ) and applies a Hann window function to the object region (I ROI ) to generate augmented image data (I H ).
A step in which the system applies image data containing an object to an object detection model to extract an object region (I ROI ); The system sets weights for scaling the central region in the Hann window function; and An object-oriented explainable model learning data augmentation method comprising the step of generating augmented image data (I H ) by applying a weighted Hann window function to an object region (I ROI ).
An object region extraction module that extracts an object region (I ROI ) by applying image data containing an object to an object detection model; and An object-oriented explainable model learning data augmentation system comprising: a data augmentation module that generates augmented image data (I H ) by setting weights for scaling a central region in a Hann window function and applying a Hann window function with weights set to an object region (I ROI ).

Description

Method and system for data augmentation for object-centric explainable model learning The present invention relates to a method and system for augmenting training data, and more specifically, to a method and system for augmenting training data used in object-oriented explainable model learning. Various deep learning models, such as image-based object detection or classification models, lack explanatory elements regarding the basis for their judgments. Consequently, although much research has recently been conducted on visual intelligence explanation techniques, there is a problem where the performance of explainable techniques is degraded by background and other factors. Accordingly, while various data augmentation methods exist for object detection or classification models, these methods are not related to explainable technology, which may lead to a problem where the performance of the learning model is not improved and explainable technology fails to focus on objects. FIG. 1 is a drawing provided for the configuration description of an object-centered explainable model learning data augmentation system according to an embodiment of the present invention, FIG. 2 is a drawing provided for a more detailed configuration description of the processor illustrated in FIG. 1. FIG. 3 is a drawing provided to explain the process of generating augmented image data through an object-centered explainable model learning data augmentation system according to an embodiment of the present invention. FIG. 4 is a drawing provided for explaining a Hann window function used in an object-centered explainable model learning data augmentation system according to an embodiment of the present invention. FIG. 5 is a flowchart provided for explaining an object-centered explainable model learning data augmentation method according to an embodiment of the present invention, and FIG. 6 is a diagram provided for the description of a visual intelligence model to which an explainable technology is applied, in which augmented image data generated through an object-centered explainable model learning data augmentation method according to an embodiment of the present invention is utilized as learning data. The present invention will be described in more detail below with reference to the drawings. To clearly explain the invention, parts unrelated to the description have been omitted from the drawings, and in the drawings, the width, length, thickness, etc., of the components may be exaggerated for convenience. FIG. 1 is a diagram provided to describe the configuration of an object-centered explainable model learning data augmentation system according to one embodiment of the present invention. The object-oriented explainable model learning data augmentation system according to the present embodiment (hereinafter collectively referred to as the 'system') is provided to augment learning data of a visual intelligence model to which explainable technology is applied. For example, to enable object-centered augmentation of training data, the system acquires image data for object detection or classification, applies the image data to an object detection model to extract object regions, and generates augmented image data for the object regions by applying a window that excludes the outer edges of the extracted object regions and enhances only the central part of the object regions. At this time, the generated augmented image data can be utilized as training data for a visual intelligence model to which explainable technology is applied. To this end, the system may include a communication unit (100), a processor (200), and a storage unit (300). The communication unit (100) is equipped with a communication module connected to a network, and can acquire image data for object detection. The storage unit (300) is provided to store programs and data necessary for the operation of the processor (200). A processor (200) is provided to handle all matters for augmenting training data. Specifically, the processor (200) can apply image data to an object detection model to extract an object region (I ROI ), set weights for scaling the center region in a Hann window function, apply a Hann window function with weights set in the object region (I ROI ), and thereby generate augmented image data (I H ). And the processor (200) can generate a training dataset based on augmented image data (I H ) and use it as training data for a visual intelligence model with explainable technology applied. Here, the training dataset may include multiple augmented image data (I H ) generated by applying different weights(s) to the same object region (I ROI ). FIG. 2 is a drawing provided for a more detailed configuration description of the processor illustrated in FIG. 1, and FIG. 3 is a drawing provided for a description of the process of generating augmented image data through an object-oriented explainable model learning data augmentation system according to an embodiment of the pr