# US 2026/0094429 A1 · Poly-scale kernel-wise convolution for high-performance visual recognition applications

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

- Number: US 2026/0094429 A1
- Document ID: US20260094429A1
- Status: Published application
- Kind: A1
- Application number: 19/370,306
- Filed: 2025-10-27
- Published: 2026-04-02
- Earliest claimed: 2025-10-27
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Anbang Yao; Xiao Zhou; Guangli Zhang; Yu Zhang; Dian Gu
- Web page: https://patentgrep.com/patent/US20260094429A1

## CPC

- G06N 3/08: Learning methods
- G06V 10/82: using neural networks
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06V 10/449: {Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters}
- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Techniques related to poly-scale kernel-wise convolutional neural network layers are discussed. A poly-scale kernel-wise convolutional neural network layer is applied to an input volume to generate an output volume and include filters each having a number of filter kernels with the same sample rate and differing dilation rates optionally in a repeating pattern of dilation rate groups within each of filters with the pattern of dilation rate groups offset between the filters the poly-scale kernel-wise convolutional neural network layer.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A non-transitory machine readable storage medium comprising instructions to cause programmable circuitry to at least:
access an input corresponding to an image, the input including a plurality of input feature maps;
process the input with a convolutional neural network (CNN), the CNN including a plurality of layers and including:
a first filter including a first kernel having a first dilation rate and a sample rate;
a second filter including a second kernel having a second dilation rate and the sample rate, the first dilation rate different than the second dilation rate; and
combine output of the first filter and the second filter to generate an output volume corresponding to the image.

### Claim 22 (depends on 21)

The non-transitory machine readable storage medium of claim 21, wherein the first dilation rate is 2 and the second dilation rate is 4.

### Claim 23 (depends on 21)

The non-transitory machine readable storage medium of claim 21, wherein the output volume includes a plurality of feature maps.

### Claim 24 (depends on 23)

The non-transitory machine readable storage medium of claim 23, wherein a number of feature maps of the output volume is equal to a number of filters in the CNN.

### Claim 25 (depends on 21)

The non-transitory machine readable storage medium of claim 21, wherein the sample rate is 3×3.

### Claim 26 (depends on 21)

The non-transitory machine readable storage medium of claim 21, wherein the output volume is an image.

### Claim 27 (depends on 21)

The non-transitory machine readable storage medium of claim 21, wherein the CNN includes a rectified linear unit (ReLU) layer.

### Claim 28

An apparatus comprising:
a memory to store at least a portion of an input corresponding to an image, the input including a plurality of input feature maps; and
a programmable circuit to:
process the input with a convolutional neural network (CNN), the CNN including a plurality of layers and including:
a first filter including a first kernel having a first dilation rate and a sample rate;
a second filter including a second kernel having a second dilation rate and the sample rate, the first dilation rate different than the second dilation rate; and
combine output of the first filter and the second filter to generate an output volume corresponding to the image.

### Claim 29 (depends on 28)

The apparatus of claim 28, wherein the first dilation rate is 2 and the second dilation rate is 4.

### Claim 30 (depends on 28)

The apparatus of claim 28, wherein the output volume includes a plurality of feature maps.

### Claim 31 (depends on 30)

The apparatus of claim 30, wherein a number of feature maps of the output volume is equal to a number of filters in the CNN.

### Claim 32 (depends on 28)

The apparatus of claim 28, wherein the sample rate is 3×3.

### Claim 33 (depends on 28)

The apparatus of claim 28, wherein the output volume is an image.

### Claim 34 (depends on 28)

The apparatus of claim 28, wherein the CNN includes a rectified linear unit (ReLU) layer.

### Claim 35

A method comprising:
accessing an input corresponding to an image, the input including a plurality of input feature maps;
processing the input with a convolutional neural network (CNN), the CNN including a plurality of layers and including:
a first filter including a first kernel having a first dilation rate and a sample rate;
a second filter including a second kernel having a second dilation rate and the sample rate, the first dilation rate different than the second dilation rate; and
combining output of the first filter and the second filter to generate an output volume corresponding to the image.

### Claim 36 (depends on 35)

The method of claim 35, wherein the first dilation rate is 2 and the second dilation rate is 4.

### Claim 37 (depends on 35)

The method of claim 35, wherein the output volume includes a plurality of feature maps.

### Claim 38 (depends on 37)

The method of claim 37, wherein a number of feature maps of the output volume is equal to a number of filters in the CNN.

### Claim 39 (depends on 35)

The method of claim 35, wherein the sample rate is 3×3.

### Claim 40 (depends on 35)

The method of claim 35, wherein the output volume is an image.
