US-20260127867-A1 - LEARNING APPARATUS AND LEARNING METHOD

Abstract

A learning apparatus includes processing circuitry configured to: acquire an inspection-target image dataset; acquire features of executed-task image datasets; extract features of the acquired inspection-target image dataset; calculate degrees of feature similarity; select one or more trained models corresponding to executed-task image datasets whose degrees of feature similarity are high in the executed-task image datasets; generate a new trained model which is a good-product distribution by inputting the acquired inspection-target image dataset to the selected trained models; determine whether precision of the generated new trained model is equal to or higher than a threshold; and output information representing the new trained model on a basis of a result of the determination.

Inventors

• Takuya Matsuda

Assignees

• MITSUBISHI ELECTRIC CORPORATION

Dates

Publication Date

20260507

Application Date

20251218

Claims (11)

1. 1 . A learning apparatus comprising: processing circuitry configured to acquire an inspection-target image dataset; acquire features of executed-task image datasets, the features being based on outputs from a plurality of intermediate layers in trained models corresponding to the executed-task image datasets; extract features of the acquired inspection-target image dataset a basis of the trained models corresponding to the executed-task image datasets and the inspection-target image dataset, the features being based on outputs from the plurality of intermediate layers in the trained models; calculate degrees of feature similarity on a basis of the features of the extracted inspection-target image dataset and the features of the executed-task image datasets having been acquired; select, on a basis of the degrees of feature similarity having been calculated, one or more trained models corresponding to executed-task image datasets whose degrees of feature similarity to the acquired inspection-target image dataset are high in the executed-task image datasets; generate a new trained model which is a good-product distribution by inputting the acquired inspection-target image dataset to the selected trained models on a basis of the acquired inspection-target image dataset and the selected trained models; determine whether precision of the generated new trained model is equal to or higher than a threshold on a basis of the generated new trained model; and output information representing the new trained model determined as having precision which is equal to or greater than the threshold on a basis of a result of the determination.
2. 2 . The learning apparatus according to claim 1 , wherein the processing circuitry is further configured to extract, as features, outputs from the plurality of intermediate layers obtained when the acquired inspection-target image dataset or a good-product image dataset in the inspection-target image dataset is input to the trained models corresponding to the executed-task image datasets.
3. 3 . The learning apparatus according to claim 1 , wherein the processing circuitry is further configured to extract, as features, vector groups obtained by averaging, channel by channel, outputs from the plurality of intermediate layers obtained when the acquired inspection-target image dataset or a good-product image dataset in the inspection-target image dataset is input to the trained models corresponding to the executed-task image datasets.
4. 4 . The learning apparatus according to claim 1 , wherein the processing circuitry is further configured to extract, as features, vectors obtained by averaging the overall outputs from the plurality of intermediate layers obtained when the acquired inspection-target image dataset or a good-product image dataset in the inspection-target image dataset is input to the trained models corresponding to the executed-task image datasets.
5. 5 . The learning apparatus according to claim 2 , wherein the processing circuitry is further configured to calculate degrees of similarity between the overall features of the extracted inspection-target image dataset and the overall features of the executed-task image datasets having been acquired using distribution differences.
6. 6 . The learning apparatus according to claim 4 , wherein the processing circuitry is further configured to calculate degrees of similarity between the overall features of the inspection-target image dataset having been extracted and the overall features of the executed-task image datasets having been acquired using common areas of distributions.
7. 7 . The learning apparatus according to claim 2 , wherein the processing circuitry is further configured to calculate a degree of similarity between a feature on each layer of the intermediate layers of the inspection-target image dataset having been extracted and a feature on a corresponding layer of the intermediate layers of the executed-task image datasets having been acquired using distribution differences.
8. 8 . The learning apparatus according to claim 4 , wherein the processing circuitry is further configured to calculate a degree of similarity between a feature on each layer of the intermediate layers of the inspection-target image dataset having been extracted and a feature on a corresponding layer of the intermediate layers of the executed-task image datasets having been acquired using common areas of distributions.
9. 9 . The learning apparatus according to claim 1 , wherein the processing circuitry is further configured to generate a new trained model which is a good-product distribution by inputting a good-product image dataset in the acquired inspection-target image dataset to the selected trained models, and combining all outputs from the respective intermediate layers.
10. 10 . The learning apparatus according to claim 1 , wherein the processing circuitry is further configured to generate a new trained model which is a good-product distribution by inputting a good-product image dataset in the acquired inspection-target image dataset to the selected trained models, and selectively combining tensors from among outputs from the respective intermediate layers.
11. 11 . A learning method comprising: acquiring an inspection-target image dataset; acquiring features of executed-task image datasets, the features being based on outputs from a plurality of intermediate layers in trained models corresponding to the executed-task image datasets; extracting features of the acquired inspection-target image dataset on a basis of the trained models corresponding to the executed-task image datasets and the inspection-target image dataset, the features being based on outputs from the plurality of intermediate layers in the trained models; calculating degrees of feature similarity on a basis of the features of the extracted inspection-target image dataset and the features of the executed-task image datasets having been acquired; selecting, on a basis of the degrees of feature similarity having been calculated, one or more trained models corresponding to executed-task image datasets whose degrees of feature similarity to the acquired inspection-target image dataset are high in the executed-task image datasets; generating a new trained model which is a good-product distribution by inputting the acquired inspection-target image dataset to the selected trained models on a basis of the acquired inspection-target image dataset and the selected trained models; determining whether an evaluation result of the generated new trained model is equal to or higher than a threshold on a basis of the generated new trained model; and outputting information representing the new trained model determined as having an evaluation result which is equal to or greater than the threshold on a basis of a result of the determination.

Description

CROSS REFERENCE TO RELATED APPLICATION This application is a Continuation of PCT International Application No. PCT/JP2023/027295, filed on Jul. 26, 2023, which is hereby expressly incorporated by reference into the present application. TECHNICAL FIELD The present disclosure relates to a learning apparatus to obtain a trained model and a learning method therefor. BACKGROUND ART In a case where AI automated visual inspection is applied to a product at a production site, it is necessary to collect inspection-target image datasets as training data for implementing a desired function. In view of this, it has conventionally been demanded to implement few-shot learning using past models such as transfer learning. On the other hand, in a case where there are a plurality of past models, it is necessary to learn and evaluate all the past models, and select the most precise model in order to obtain a model optimum for inspection-target image datasets. Accordingly, in a case where the number of past models is enormous, a huge learning cost is incurred to obtain the optimum model. In view of this, techniques to select a past model on the basis features of image datasets and the like, and perform transfer learning have been proposed. For example, examples of the transfer learning technologies described above include a technology disclosed in Patent Literature 1. This technology adopts a scheme in which a plurality of AI models are combined to increase the precision of inspecting good products and bad products of a product. In this technology, first, inspection data is input to a plurality of past models, and past models whose intermediate outputs or final outputs are correlated at degrees which are equal to or lower than a certain value are selected. Then, a plurality of hybrid model candidates are created using the selected models. Then, the most precise one is adopted from the hybrid model candidates. In this manner, in this technology, inspection data is input to a plurality of hybrid models, and learning is performed such that label determination is performed correctly on the basis of the weighted sum of outputs of the respective models. CITATION LIST Patent Literature Patent Literature 1: WO 2022/215559 SUMMARY OF INVENTION Technical Problem As described above, in the existing transfer learning technology, a plurality of pairs of models whose intermediate outputs or final outputs that are obtained when inspection data (inspection-target image datasets) is input to the past models are correlated at low degrees are selected. In this case, the models are independent of each other, but there is a possibility that models appropriate for the inspection data cannot be selected. The present disclosure has been made to solve the problem described above, and an object thereof is to provide a learning apparatus that makes it possible to obtain a trained model appropriate for an inspection-target image dataset as compared to conventional techniques. Solution to Problem A learning apparatus according to the present disclosure includes: processing circuitry configured to: acquire an inspection-target image dataset; acquire features of executed-task image datasets, the features being based on outputs from a plurality of intermediate layers in trained models corresponding to the executed-task image datasets; extract features of the acquired inspection-target image dataset a basis of the trained models corresponding to the executed-task image datasets and the inspection-target image dataset, the features being based on outputs from the plurality of intermediate layers in the trained models; calculate degrees of feature similarity on a basis of the features of the extracted inspection-target image dataset and the features of the executed-task image datasets having been acquired; select, on a basis of the degrees of feature similarity having been calculated, one or more trained models corresponding to executed-task image datasets whose degrees of feature similarity to the acquired inspection-target image dataset are high in the executed-task image datasets; generate a new trained model which is a good-product distribution by inputting the acquired inspection-target image dataset to the selected trained models on a basis of the acquired inspection-target image dataset and the selected trained models; determine whether precision of the generated new trained model is equal to or higher than a threshold on a basis of the generated new trained model; and output information representing the new trained model determined as having precision which is equal to or greater than the threshold on a basis of a result of the determination. Advantageous Effects of Invention Since the present disclosure adopts the configuration described above, it becomes possible to obtain a trained model appropriate for an inspection-target image dataset as compared to conventional techniques. BRIEF DESCRIPTION OF DRAWINGS FIG. 1 is a block diagram illustrating a con