GAN Training via Loss Maximization for Image Diversity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image generation methods struggle to produce diverse and realistic images when trained with small datasets, often leading to overfitting and poor performance in image classification tasks.

Innovation Solution

A method for training a generative adversarial network (GAN) that maximizes a loss function characterizing the difference between images generated for different input values, allowing the GAN to generate diverse and realistic images even with a single training image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If known image generation methods are used with small training datasets, then the training process is faster and less costly, but the generated images suffer from overfitting and lack diversity

Engineering Contradiction:
Improvetraining speedVSAvoidimage diversity
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent changes the optimization parameter from minimizing to maximizing the loss function. This parameter inversion fundamentally alters the training dynamics, enabling the generator to produce diverse images by seeking regions of the data manifold that are far from the training distribution, thereby preventing overfitting while maintaining training efficiency

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent applies preliminary anti-action by intentionally training the generator to produce images that are maximally different from the training data. This counterintuitive approach prevents overfitting in advance by directing the generator away from memorizing training examples and toward exploring diverse regions of the data space

Inventive Principle:
Principle #9Preliminary anti-action

2Reliability

If more training images are obtained to avoid overfitting, then image diversity improves, but the time and cost required for recording and processing images increases

Engineering Contradiction:
Improveimage diversityVSAvoiddata collection time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent creates synthetic copies of training images through the generator that are maximally diverse. Instead of collecting more real images, the system generates artificial variations that expand the effective training distribution, eliminating the need for time-consuming data collection while maintaining image diversity

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent inverts the conventional approach by not trying to make generated images similar to training images, but rather maximally different. This inversion allows the system to achieve diversity without requiring additional training data, as the generator learns to explore the boundaries and extremes of the data manifold

Inventive Principle:
Principle #13The other way round (Inversion)

3Reliability

If the generator is regularized to produce diverse outputs, then image diversity improves, but the training complexity and computational requirements increase

Engineering Contradiction:
Improveimage diversityVSAvoidtraining complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts the diversity objective from complex regularization mechanisms and embeds it directly into the core loss function through maximization. This simplifies the training process by making diversity the primary optimization goal rather than an additional constraint, reducing training complexity while maintaining diversity

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4047524B1Device and method for training a machine learning system for generating images
Publication Date: 2025.04.09 ROBERT BOSCH GMBH
  • EP4047524B1 patent drawingFigure 1
  • EP4047524B1 patent drawingFigure 2
  • EP4047524B1 patent drawingFigure 3

AI summary

Computer-implemented method for training a generative adversarial network (60), wherein a generator (61) of the generative adversarial network (60) is configured to generate at least one image (x1) based on at least one input value (z), wherein training the generative adversarial network (60) comprises maximizing a loss function ( ) that characterizes a difference between a first image (x1) determined by the generator (61) for at least one first input value and a third image determined by the generator (61) for at least one second input value.