Spectral Transformer Classification With Global-Local Feature Splitting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Transformer models face challenges in efficiently capturing both global and local information from large datasets, leading to increased computational complexity and loss of informational integrity, particularly in applications like medical imaging.

Innovation Solution

The integration of spectral transformations, specifically using the Hartley Transform with convolutional operators in initial layers, combined with deeper attention layers, reduces computational complexity while retaining informational integrity by capturing both global and local features.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If transformer models use multiple attention layers to capture global and local information, then classification accuracy is improved, but computational complexity increases quadratically

Engineering Contradiction:
Improveclassification accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the embedding space into multiple distinct regions (e.g., global features region, local features region, texture features region) and assigns different attention mechanisms to process different segments. This allows the model to capture various types of information in parallel without requiring all tokens to attend to all other tokens, thus reducing quadratic complexity while maintaining comprehensive feature extraction capability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension by adding spatial position embeddings and depth-wise separable convolutions to the transformer architecture. This transforms the problem from purely sequence-based attention to a multi-dimensional processing approach where spatial and channel dimensions are handled separately, reducing the computational burden while preserving the ability to capture global and local dependencies.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Loss of information

If input data is split into tokens and processed through embedding layers, then feature representation is enhanced, but information loss occurs during tokenization

Engineering Contradiction:
Improveinformational integrityVSAvoidfeature representation quality
Core Design Contradiction:
Loss of informationVSMeasurement precision

Solution Approach 1:

The patent merges multiple types of embeddings (patch embeddings, position embeddings, class embeddings) into a unified embedding space that preserves both local patch information and global positional context. By combining these different embedding types rather than processing them separately, the model maintains complete information from the original input while enabling sophisticated feature representation through the unified embedding structure.

Inventive Principle:
Principle #5Merging (Combining)

3Loss of information

If the context window includes all tokens for attention processing, then global context is captured, but computational resources are excessively consumed

Engineering Contradiction:
Improveglobal context captureVSAvoidcomputational resources
Core Design Contradiction:
Loss of informationVSUse of energy by moving object

Solution Approach 1:

The patent applies different attention mechanisms to different regions of the embedding space based on their specific requirements. Global feature regions use simplified attention or pooling operations, while local feature regions use more sophisticated attention mechanisms. This localized approach ensures that global context is captured where necessary without applying computationally expensive operations uniformly across the entire input, thus reducing overall computational resource consumption.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4586139B1Transformer for classification
Publication Date: 2026.03.25 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4586139B1 patent drawingFigure 1
  • EP4586139B1 patent drawingFigure 2
  • EP4586139B1 patent drawingFigure 3

AI summary

A method may embed the input dataset into a first embedding space. A method may input the first embedding space into a spectral module including a periodic information processor and an aperiodic information processor. A method may identify global features in the input dataset using the periodic information processor based on a first subset of the first embedding space. A method may identify first local features in the input dataset using the aperiodic information processor based on a second subset of the first embedding space, wherein the first subset and the second subset are different. A method may combine the global features and the first local features into a dataset of classified features of the input dataset.