# US 2025/0148815 A1 · Gradient-to-parameter ratio guided feature alignment for model adaptation

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

- Number: US 2025/0148815 A1
- Document ID: US20250148815A1
- Status: Published application
- Kind: A1
- Application number: 18/938,766
- Filed: 2024-11-06
- Published: 2025-05-08
- Earliest claimed: 2023-11-08
- Assignees: NEC Laboratories America, Inc.
- Applicants: NEC Laboratories America, Inc.
- Inventors: Eric Cosatto; Evgenia Tatiani Chroni
- Web page: https://patentgrep.com/patent/US20250148815A1

## CPC

- G06V 20/698: {Matching; Classification}
- G06T 7/0012: {Biomedical image inspection}
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Systems and methods for gradient-to-parameter ratio guided feature alignment for model adaptation. To adapt an artificial intelligence (AI) model to different domains, activation statistics for the AI model can be computed from collected domain data. Weights of the AI model can be adjusted based on the activation statistics of the training gradients. The AI model can be fine-tuned by focusing adaptation intensity to layers with attention mechanism by using a ratio of gradient norm over parameter norm to obtain a fine-tuned AI model. The fine-tuned AI model can be employed to perform downstream tasks such as cell segmentation from medical images.

## Claims

### Claim 1

A computer-implemented method for adapting artificial intelligence (AI) models to different domains, comprising:
computing activation statistics for an AI model from collected domain data;
adjusting weights of layers of the AI model based on the activation statistics by employing metrics of training gradients;
fine-tuning the AI model by focusing adaptation intensity to layers with attention mechanism by using a ratio of gradient norm over parameter norm to obtain a fine-tuned AI model; and
performing downstream tasks with healthcare images using the fine-tuned AI model.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein performing the downstream tasks further comprises performing cancer cell detection from healthcare images to assist a decision-making process of a healthcare provider.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein performing the downstream tasks further comprises updating a medical diagnosis for a patient based on the results of the cancer cell detection.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein computing the activation statistics further comprises conducting a forward pass through the AI model with frozen parameters.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein adjusting the weights of the layers further comprises optimizing model parameters by minimizing an average of layer-wise losses.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein optimizing the model parameters further comprises computing the layer-wise loss as the distance between source data statistics and target data statistics for each batch from the target data.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein fine-tuning the AI model further comprises minimizing an alignment loss that is weighted by respective gradient to parameter norm ratio and a layer-wise loss for the layers of the AI model.

### Claim 8

A system for adapting artificial intelligence (AI) models to different domains, comprising:
a memory device;
one or more processor devices operatively coupled with the memory device to:
compute activation statistics for an AI model from collected domain data;
adjust weights of layers of the AI model based on the activation statistics by employing metrics of training gradients;
fine-tune the AI model by focusing adaptation intensity to layers with attention mechanism by using a ratio of gradient norm over parameter norm to obtain a fine-tuned AI model; and
perform downstream tasks with healthcare images using the fine-tuned AI model.

### Claim 9 (depends on 8)

The system of claim 8, wherein to perform the downstream tasks further comprises to perform cancer cell detection from healthcare images to assist a decision-making process of a healthcare provider.

### Claim 10 (depends on 9)

The system of claim 9, wherein to perform the downstream tasks further comprises to update a medical diagnosis for a patient based on the results of the cancer cell detection.

### Claim 11 (depends on 8)

The system of claim 8, wherein to compute the activation statistics further comprises to conduct a forward pass through the AI model with frozen parameters.

### Claim 12 (depends on 8)

The system of claim 8, wherein to adjusting the weights of the layers further comprises to optimize model parameters by minimizing an average of layer-wise losses.

### Claim 13 (depends on 12)

The system of claim 12, wherein to optimize the model parameters further comprises to compute the layer-wise loss as the distance between source data statistics and target data statistics for each batch from the target data.

### Claim 14 (depends on 1)

The computer-implemented method of claim 1, wherein to fine-tune the AI model further comprises to minimize an alignment loss that is weighted by respective gradient to parameter norm ratio and a layer-wise loss for the layers of the AI model.

### Claim 15

A non-transitory computer program product comprising a computer-readable storage medium including program code for adapting artificial intelligence (AI) models to different domains, wherein the program code when executed on a computer causes the computer to:
compute activation statistics for an AI model from collected domain data;
adjust weights of layers of the AI model based on the activation statistics by employing metrics of training gradients;
fine-tune the AI model by focusing adaptation intensity to layers with attention mechanism by using a ratio of gradient norm over parameter norm to obtain a fine-tuned AI model; and
perform downstream tasks with healthcare images using the fine-tuned AI model.

### Claim 16 (depends on 15)

The non-transitory computer program product of claim 15, wherein to perform the downstream tasks further comprises to perform cancer cell detection from healthcare images to assist a decision-making process of a healthcare provider.

### Claim 17 (depends on 15)

The non-transitory computer program product of claim 15, wherein to compute the activation statistics further comprises to conduct a forward pass through the AI model with frozen parameters.

### Claim 18 (depends on 15)

The non-transitory computer program product of claim 15, wherein to adjusting the weights of the layers further comprises to optimize model parameters by minimizing an average of layer-wise losses.

### Claim 19 (depends on 18)

The non-transitory computer program product of claim 18, wherein to optimize the model parameters further comprises to compute the layer-wise loss as the distance between source data statistics and target data statistics for each batch from the target data.

### Claim 20 (depends on 15)

The non-transitory computer program product of claim 15, wherein to fine-tune the AI model further comprises to minimize an alignment loss that is weighted by respective gradient to parameter norm ratio and a layer-wise loss for the layers of the AI model.
