Patent
US 11,514,694Teaching GAN (Generative Adversarial Networks) to Generate Per-Pixel Annotation
Danil Fanilievich GALEEV
US
Copyright © 2026 Matter42. All rights reserved.
Patent
Atlas literature
Patent
US 11,514,694Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a block diagram illustrating a conf i guration of an electronic apparatus according to an embodiment; [0018]
FIG. 2 is a flowchart illustrating an image synthesis method and an annotation synthesis method according to an embodiment; [0019]
FIG. 3 is a flowchart illustrating an example of generating synthetic data using a GAN and a decoder; [0020]
FIG. 4B is a block diagram illustrating a network architecture, according to an embodiment, in greater detail; [0022]
FIG. 5 is an example of a generated image from Sty l eGAN-FFHQ and a corresponding generated annotation for hair segmentation; [0023]
FIGS. 6A to 6D each illustrate a comparison of a proposed method to a baseline on LS U N-interiors for a varying number of training samples; [0024]
FIG. 7 illustrates segmentation masks for cars from LS U N dataset; [0025]
FIG. 8 illustrates a Sty l eGAN and a predicted mask, wherein a separate segmentation network is not trained; and [0026]
FIG. 9 illustrates synthetic images from Sty l eGAN trained on FFHQ dataset and the proposed segmentation masks of a front right tooth.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The method of claim 1, further comprising: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The method of claim 1, further comprising displaying the first image and the first segmentation mask. Original
The method of claim 1, wherein the decoder is a light-weight decoder that Original
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder; and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
An electronic apparatus comprising: a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, and obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, wherein the at least one processor is further configured to obtain the first semantic segmentation mask corresponding to the first image from the decoder according to input of the first feature value. Currently amended
The electronic apparatus of claim 7, wherein: the decoder is trained based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN; and the at least one processor is con f igured to input, to the trained decoder, the first feature value obtained from the at l east one intermediate layer of the GAN, to obtain the first semantic segmentation mask. Original
The electronic apparatus of claim 7, further comprising: a display, wherein the at least one processor is further configured to control output, via the display, the first image and the first segmentation mask. Original
The electronic apparatus of claim 7, wherein the decoder is a light-weight AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ Original
An electronic apparatus comprising: AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, train a semantic segmentation network to, based on a third image being input to the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
A non-transitory computer readable medium having stored therein a computer instruction executable by at least one processor of an electronic apparatus to perform a method comprising: inputting data to a generative adversarial network (GAN) to obtain a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Original
The non-transitory computer readable medium of claim 13, wherein the decoder is a light-weight decoder that has a smaller number of parameters than the GAN. Original
Canceled
Patent
Atlas literature
Patent
US 11,514,694Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a block diagram illustrating a conf i guration of an electronic apparatus according to an embodiment; [0018]
FIG. 2 is a flowchart illustrating an image synthesis method and an annotation synthesis method according to an embodiment; [0019]
FIG. 3 is a flowchart illustrating an example of generating synthetic data using a GAN and a decoder; [0020]
FIG. 4B is a block diagram illustrating a network architecture, according to an embodiment, in greater detail; [0022]
FIG. 5 is an example of a generated image from Sty l eGAN-FFHQ and a corresponding generated annotation for hair segmentation; [0023]
FIGS. 6A to 6D each illustrate a comparison of a proposed method to a baseline on LS U N-interiors for a varying number of training samples; [0024]
FIG. 7 illustrates segmentation masks for cars from LS U N dataset; [0025]
FIG. 8 illustrates a Sty l eGAN and a predicted mask, wherein a separate segmentation network is not trained; and [0026]
FIG. 9 illustrates synthetic images from Sty l eGAN trained on FFHQ dataset and the proposed segmentation masks of a front right tooth.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The method of claim 1, further comprising: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The method of claim 1, further comprising displaying the first image and the first segmentation mask. Original
The method of claim 1, wherein the decoder is a light-weight decoder that Original
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder; and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
An electronic apparatus comprising: a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, and obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, wherein the at least one processor is further configured to obtain the first semantic segmentation mask corresponding to the first image from the decoder according to input of the first feature value. Currently amended
The electronic apparatus of claim 7, wherein: the decoder is trained based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN; and the at least one processor is con f igured to input, to the trained decoder, the first feature value obtained from the at l east one intermediate layer of the GAN, to obtain the first semantic segmentation mask. Original
The electronic apparatus of claim 7, further comprising: a display, wherein the at least one processor is further configured to control output, via the display, the first image and the first segmentation mask. Original
The electronic apparatus of claim 7, wherein the decoder is a light-weight AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ Original
An electronic apparatus comprising: AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, train a semantic segmentation network to, based on a third image being input to the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
A non-transitory computer readable medium having stored therein a computer instruction executable by at least one processor of an electronic apparatus to perform a method comprising: inputting data to a generative adversarial network (GAN) to obtain a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Original
The non-transitory computer readable medium of claim 13, wherein the decoder is a light-weight decoder that has a smaller number of parameters than the GAN. Original
Canceled
Patent
Atlas literature
Patent
US 11,514,694Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a block diagram illustrating a conf i guration of an electronic apparatus according to an embodiment; [0018]
FIG. 2 is a flowchart illustrating an image synthesis method and an annotation synthesis method according to an embodiment; [0019]
FIG. 3 is a flowchart illustrating an example of generating synthetic data using a GAN and a decoder; [0020]
FIG. 4B is a block diagram illustrating a network architecture, according to an embodiment, in greater detail; [0022]
FIG. 5 is an example of a generated image from Sty l eGAN-FFHQ and a corresponding generated annotation for hair segmentation; [0023]
FIGS. 6A to 6D each illustrate a comparison of a proposed method to a baseline on LS U N-interiors for a varying number of training samples; [0024]
FIG. 7 illustrates segmentation masks for cars from LS U N dataset; [0025]
FIG. 8 illustrates a Sty l eGAN and a predicted mask, wherein a separate segmentation network is not trained; and [0026]
FIG. 9 illustrates synthetic images from Sty l eGAN trained on FFHQ dataset and the proposed segmentation masks of a front right tooth.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The method of claim 1, further comprising: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The method of claim 1, further comprising displaying the first image and the first segmentation mask. Original
The method of claim 1, wherein the decoder is a light-weight decoder that Original
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder; and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
An electronic apparatus comprising: a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, and obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, wherein the at least one processor is further configured to obtain the first semantic segmentation mask corresponding to the first image from the decoder according to input of the first feature value. Currently amended
The electronic apparatus of claim 7, wherein: the decoder is trained based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN; and the at least one processor is con f igured to input, to the trained decoder, the first feature value obtained from the at l east one intermediate layer of the GAN, to obtain the first semantic segmentation mask. Original
The electronic apparatus of claim 7, further comprising: a display, wherein the at least one processor is further configured to control output, via the display, the first image and the first segmentation mask. Original
The electronic apparatus of claim 7, wherein the decoder is a light-weight AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ Original
An electronic apparatus comprising: AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, train a semantic segmentation network to, based on a third image being input to the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
A non-transitory computer readable medium having stored therein a computer instruction executable by at least one processor of an electronic apparatus to perform a method comprising: inputting data to a generative adversarial network (GAN) to obtain a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Original
The non-transitory computer readable medium of claim 13, wherein the decoder is a light-weight decoder that has a smaller number of parameters than the GAN. Original
Canceled
Patent
Atlas literature
Patent
US 11,514,694Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a block diagram illustrating a conf i guration of an electronic apparatus according to an embodiment; [0018]
FIG. 2 is a flowchart illustrating an image synthesis method and an annotation synthesis method according to an embodiment; [0019]
FIG. 3 is a flowchart illustrating an example of generating synthetic data using a GAN and a decoder; [0020]
FIG. 4B is a block diagram illustrating a network architecture, according to an embodiment, in greater detail; [0022]
FIG. 5 is an example of a generated image from Sty l eGAN-FFHQ and a corresponding generated annotation for hair segmentation; [0023]
FIGS. 6A to 6D each illustrate a comparison of a proposed method to a baseline on LS U N-interiors for a varying number of training samples; [0024]
FIG. 7 illustrates segmentation masks for cars from LS U N dataset; [0025]
FIG. 8 illustrates a Sty l eGAN and a predicted mask, wherein a separate segmentation network is not trained; and [0026]
FIG. 9 illustrates synthetic images from Sty l eGAN trained on FFHQ dataset and the proposed segmentation masks of a front right tooth.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The method of claim 1, further comprising: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The method of claim 1, further comprising displaying the first image and the first segmentation mask. Original
The method of claim 1, wherein the decoder is a light-weight decoder that Original
A controlling method of an electronic apparatus, the method comprising: by inputting data to a generative adversarial network (GAN), obtaining a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder; and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
An electronic apparatus comprising: a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, and obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, wherein the at least one processor is further configured to obtain the first semantic segmentation mask corresponding to the first image from the decoder according to input of the first feature value. Currently amended
The electronic apparatus of claim 7, wherein: the decoder is trained based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN; and the at least one processor is con f igured to input, to the trained decoder, the first feature value obtained from the at l east one intermediate layer of the GAN, to obtain the first semantic segmentation mask. Original
The electronic apparatus of claim 7, further comprising: a display, wherein the at least one processor is further configured to control output, via the display, the first image and the first segmentation mask. Original
The electronic apparatus of claim 7, wherein the decoder is a light-weight AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ Original
An electronic apparatus comprising: AMENDMENT UNDER 37 C.F.R. § 1.111 Attorney Docket No.: Q₂₅₅₄₃₀ a memory storing a decoder and a generative adversarial network (GAN) trained to generate an image based on input data; and at least one processor configured to: obtain a first image from the GAN by inputting data to the GAN, input, to the decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN, obtain a first semantic segmentation mask from the decoder according to the input of the first feature value to the decoder, and based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, train a semantic segmentation network to, based on a third image being input to the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Currently amended
Canceled
A non-transitory computer readable medium having stored therein a computer instruction executable by at least one processor of an electronic apparatus to perform a method comprising: inputting data to a generative adversarial network (GAN) to obtain a first image from the GAN; inputting, to a decoder, a first feature value that is obtained from at least one intermediate layer of the GAN according to the inputting of the data to the GAN; and obtaining a first semantic segmentation mask from the decoder according to the inputting of the first feature value to the decoder, wherein the obtaining the first semantic segmentation mask comprises obtaining the first semantic segmentation mask corresponding to the first image from the decoder according to the inputting of the first feature value. Currently amended
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on a second feature value that is obtained from the at least one intermediate layer of the GAN and a second semantic segmentation mask that is added to a second image output from the GAN, training the decoder to output a semantic segmentation mask based on a feature value obtained from the at least one intermediate layer of the GAN being input to the decoder, wherein the inputting the first feature value comprises inputting the first feature value to the trained decoder. Original
The non-transitory computer readable medium of claim 13, wherein the method further comprises: based on the first image obtained from the GAN and the first semantic segmentation mask obtained from the decoder, training a semantic segmentation network to, based on a third image being input the semantic segmentation network, output at least one semantic segmentation mask corresponding to the third image. Original
The non-transitory computer readable medium of claim 13, wherein the decoder is a light-weight decoder that has a smaller number of parameters than the GAN. Original
Canceled