IP Library Granted Patent US 12670699
Granted Patent B2
US 12670699 · App. 18/739,056 · Granted Jun 30, 2026

Systems and methods for PatchSwap—a regularization technique for vision transformers

Inventors: Baoxin Li (Chandler, AZ); Sachin Chhabra (Tempe, AZ)
Assignee: Arizona Board of Regents on Behalf of Arizona State University
G06V10/774G06T5/50G06T2207/20221
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12670699
App. No.
18/739,056
Granted
Jun 30, 2026
Kind
B2
Abstract

Examples of a computer-implemented regularization technique are described and tailor-made for Vision Transformers. Examples can combine two or more input images and swap patches between them to produce a PatchSwap image. The PatchSwap image is then used to train a Vision Transformer to predict the mixing ratio as well as the categories of the original images.

Claims (12)

1 . A system for regularizing Vision Transformers, comprising:

a processor in communication with a memory, the memory including instructions executable by the processor to:

access a plurality of input images;

access a parameter for a patch size;

generate a plurality of patched images from the plurality of input images by:

selecting a first image in the plurality of images and selecting a second image in the plurality of images,

dividing the first image and the second image into a plurality of patches of equal size based on the parameter for patch size,

determining a mixing ratio for selecting a proportion of patches from the first image and proportion of patches from the second image;

generate a patched image based on the first image, the second image, and the mixing ratio, wherein the patched image is comprised of patches from the first image and the second image and the relative position of the patches from the first image and the patches from the second image remains consistent; and

train a model based on the plurality of patched images.

2 . The system of claim 1 , further comprising using a supervised approach.

3 . The system of claim 1 , further comprising using a semi-supervised approach.