# US 2026/0228525 A1 · Dynamic class-incremental learning without forgetting

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

- Number: US 2026/0228525 A1
- Document ID: US20260228525A1
- Status: Published application
- Kind: A1
- Application number: 19/153,308
- Filed: 2023-03-24
- Published: 2026-08-06
- Earliest claimed: 2023-03-24
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Haijun ZHAO; Yinxiong YAO
- Web page: https://patentgrep.com/patent/US20260228525A1

## CPC

- G06N 3/08: Learning methods
- G06V 10/82: using neural networks
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/096: Transfer learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A processor-implemented method for dynamic class-incremental learning without forgetting includes receiving, by an artificial neural network (ANN), an input. The ANN extracts features of the input to generate a representation of the input. An embedding is generated by the ANN based on the representation and multiple similarity metrics. The ANN generates a new class without retraining the ANN. The new class is generated based on a comparison of the embedding and a set of prior embeddings.

## Claims

### Claim 1

A processor-implemented method, comprising:
receiving, by a first artificial neural network (ANN), an input;
extracting, by the first ANN, features of the input to generate a representation of the input;
generating, by the first ANN, an embedding based on the representation and multiple similarity metrics; and
generating, by the first ANN, a new class without retraining the first ANN, the new class being generated based on a comparison of the embedding and a set of prior embeddings.

### Claim 2 (depends on 1)

The processor-implemented method of claim 1, in which the first ANN is trained based on a multiple similarity loss function.

### Claim 3 (depends on 2)

The processor-implemented method of claim 2, in which the first ANN is implemented at a server and the method further comprises:
training a second ANN, based on the multiple similarity loss function; and
distributing, by the server, the second ANN model to a user device.

### Claim 4 (depends on 1)

The processor-implemented method of claim 1, further comprising determining a score for a pair of samples based on the multiple similarity metrics for the pair of samples included in the input, the embedding being generated based on the score.

### Claim 5 (depends on 1)

The processor-implemented method of claim 1, further comprising:
mining the input and training samples to determine pairs of similar samples, the pairs of similar samples being determined based on a self-similarity and a relative similarity; and
assigning a weight to the pairs of similar samples based on the self-similarity and the relative similarity.

### Claim 6

A processor-implemented method, comprising:
receiving, by an artificial neural network (ANN) at a user device, an input;
extracting, by the ANN, features of the input to generate a representation of the input;
generating, by the ANN, an input embedding based on the representation and a learned multiple similarity;
comparing the input embedding to a set of embeddings stored at the user device; and
generating an inference for the input based on the comparison of the input embedding and the set of embeddings.

### Claim 7 (depends on 6)

The processor-implemented method of claim 6, further comprising:
determining that the input comprises unseen data;
generating an index for the embedding corresponding to the unseen data; and
storing the embedding with the set of embeddings at the user device.

### Claim 8 (depends on 7)

The processor-implemented method of claim 7, further comprising generating, by the ANN, a new class, the embedding corresponding to the unseen data being a prototype for the new class, and the new class being added without retraining the ANN.

### Claim 9

An apparatus, comprising:
a memory; and
at least one processor coupled to the memory, the at least one processor configured:
to receive, by a first artificial neural network (ANN), an input, the first ANN being trained based on a multiple similarity loss function;
to extract, by the first ANN, features of the input to generate a representation of the input;
to generate, by the first ANN, an embedding based on the representation and multiple similarity metrics; and
to generate, by the first ANN, a new class without retraining the first ANN, the new class being generated based on a comparison of the embedding and a set of prior embeddings.

### Claim 10 (depends on 9)

The apparatus of claim 9, in which the first ANN is trained based on a multiple similarity loss function.

### Claim 11 (depends on 10)

The apparatus of claim 10, in which the first ANN is implemented at a server and the at least one processor is further configured:
to train a second ANN, based on the multiple similarity loss function; and
to distribute, by the server, the second ANN model to a user device.

### Claim 12 (depends on 9)

The apparatus of claim 9, in which the at least one processor is further configured to determine a score for a pair of samples based on the multiple similarity metrics for the pair of samples included in the input, the embedding being generated based on the score.

### Claim 13 (depends on 9)

The apparatus of claim 9, in which the at least one processor is further configured:
to mine the input and training samples to determine pairs of similar samples, the pairs of similar samples being determined based on a self-similarity and a relative similarity; and
to assign a weight to the pairs of similar samples based on the self-similarity and the relative similarity.

### Claim 14

An apparatus, comprising:
a memory; and
at least one processor coupled to the memory, the at least one processor configured:
to receive, by an artificial neural network (ANN) at a user device, an input;
to extract, by the ANN, features of the input to generate a representation of the input;
to generate, by the ANN, an input embedding based on the representation and a learned multiple similarity;
to compare the input embedding to a set of embeddings stored at the user device; and
to generate an inference for the input based on the comparison of the input embedding and the set of embeddings.

### Claim 15 (depends on 14)

The apparatus of claim 14, in which the at least one processor is further configured:
to determine that the input comprises unseen data;
to generate an index for the embedding corresponding to the unseen data; and
to store the embedding with the set of embeddings at the user device.

### Claim 16 (depends on 15)

The apparatus of claim 15, in which the at least one processor is further configured to generate, by the ANN, a new class, the embedding corresponding to the unseen data being a prototype for the new class, and the new class being added without retraining the ANN.
