# US 2025/0157201 A1 · Explanation of machine-learned models using image translation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0157201 A1
- Document ID: US20250157201A1
- Status: Published application
- Kind: A1
- Application number: 19/020,516
- Filed: 2025-01-14
- Published: 2025-05-15
- Earliest claimed: 2022-08-15
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Arunachalam Narayanaswamy; Subhashini Venugopalan; Avinash Vaidyanathan Varadarajan
- Web page: https://patentgrep.com/patent/US20250157201A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06V 10/776: Validation; Performance evaluation
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/048: Activation functions
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G06N 3/094: Adversarial learning
- G06V 10/772: Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
- G06V 10/82: using neural networks
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30004: Biomedical image processing
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods for identifying visual features that influence a predictive model are provided. The technology employs an image translation function to introduce a visual feature into an image to create a modified image that can be fed to a predictive model. When the predictive model generates a different prediction for a given image than it does for a modified version of that image, the image translation function can then be used to make further modified versions that exaggerate the introduced visual feature. The technology thus aids in identifying visual features that influence the predictive model so that the model's conclusions can be understood, and so that those visual features can be further studied and tested.

## Claims

### Claim 1

A computer-implemented method for identifying visual features involving model prediction, the method comprising:
generating, by one or more processors, a prediction based on a given image using a predictive model, wherein the given image includes a visual feature created by altering at least a portion of another image using a translation function; and
modifying, by the one or more processors, at least a portion of the given image using the translation function to create a new image in which the visual feature is modified relative to the given image;
wherein the translation function is configured to translate a first class of imagery to appear more like a second class of imagery.

### Claim 2 (depends on 1)

The method of claim 1, wherein the modified visual feature is amplified relative to the given image.

### Claim 3 (depends on 1)

The method of claim 1, wherein the modified visual feature is exaggerated relative to the given image.

### Claim 4 (depends on 1)

The method of claim 1, wherein the translation function is obtained via a generative adversarial network.

### Claim 5 (depends on 1)

The method of claim 1, wherein the predictive model comprises a neural network.

### Claim 6 (depends on 1)

The method of claim 1, wherein the visual feature included in the new image is created by modifying only a portion of the given image using the translation function.

### Claim 7 (depends on 6)

The method of claim 6, further comprising identifying, by the one or more processors, the portion of the given image using spatial explanation.

### Claim 8 (depends on 7)

The method of claim 7, wherein the spatial explanation employs a perturbation-based model.

### Claim 9 (depends on 7)

The method of claim 7, wherein the spatial explanation employs a backpropagation-based model.

### Claim 10 (depends on 6)

The method of claim 6, further comprising:
generating, by the one or more processors, another prediction based on an ablated version of the given image; and
identifying, by the one or more processors, the portion of the given image based on the ablated version of the given image.

### Claim 11

A processing system comprising:
memory; and
one or more processors coupled to the memory and configured to:
generate a prediction based on a given image using a predictive model, wherein the given image includes a visual feature created by altering at least a portion of another image using a translation function; and
modify at least a portion of the given image using the translation function to create a new image in which the visual feature is modified relative to the given image;
wherein the translation function is configured to translate a first class of imagery to appear more like a second class of imagery.

### Claim 12 (depends on 11)

The system of claim 11, wherein the modified visual feature is amplified relative to the given image.

### Claim 13 (depends on 11)

The system of claim 11, wherein the modified visual feature is exaggerated relative to the given image.

### Claim 14 (depends on 11)

The system of claim 11, wherein the translation function is obtained using a generative adversarial network.

### Claim 15 (depends on 11)

The system of claim 11, wherein the predictive model comprises a neural network.

### Claim 16 (depends on 11)

The system of claim 11, wherein the visual feature included in the new image is created by modifying only a portion of the given image using the translation function.

### Claim 17 (depends on 16)

The system of claim 16, wherein the one or more processors are further configured to identify the portion of the given image using spatial explanation.

### Claim 18 (depends on 17)

The system of claim 17, wherein the spatial explanation employs a perturbation-based model.

### Claim 19 (depends on 17)

The system of claim 17, wherein the spatial explanation employs a backpropagation-based model.

### Claim 20 (depends on 16)

The system of claim 16, wherein the one or more processors are further configured to:
generate another prediction based on an ablated version of the given image; and
identify the portion of the given image based on the ablated version of the given image.
