Systems and methods for image classification
The proposed classification ML model with a backbone and generative component addresses the challenge of one-shot class-incremental learning by leveraging residual space mapping, enhancing novel class recognition and maintaining accuracy on user devices with minimal resources.
WO2026135190A1PCT designated stage Publication Date: 2026-06-25SAMSUNG ELECTRONICS CO LTD
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SAMSUNG ELECTRONICS CO LTD
- Filing Date
- 2025-12-16
- Publication Date
- 2026-06-25
Smart Images
Figure KR2025021924_25062026_PF_FP_ABST
Abstract
Broadly speaking, the present techniques generally relate to a method of generating a classification machine learning, ML model comprising a base ML feature embedding model and a generative ML model for deployment to a user device and a method of using the classification ML model which has been generated. The present techniques also relate to a method of generating a training data set for training the ML generative model to improve the classification of input images, The present techniques relate to devices and systems for carrying out the methods. Advantageously, the present techniques enable class-incremental recognition of personal object classes via conditional feature-space generative modelling with near-zero forgetting.
Need to check novelty before this filing date? Find Prior Art