System and Method for Contrastive Affinity Learning Via Auxiliary Prompts for Generalized Novel Category Discovery
Zhang, Sheng Khan, Salman Shen, Zhiqiang Naseer, Muzammal Chen, Guangyi Khan, Fahad
Zhang, Sheng
Khan, Salman
Shen, Zhiqiang
Naseer, Muzammal
Chen, Guangyi
Khan, Fahad
Supervisor
Department
Computer Vision
Embargo End Date
Type
Patent
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
A system and method of fine-grained image category discovery with few human annotations includes a camera and a trained machine learning model, which predicts a label for an object in a captured image and outputs the predicted label. The machine learning model is trained by contrastive affinity learning, including retrieving images having an object, a warm-up stage in which semi-supervised contrastive learning is performed based on projected features of a class token and an ensembled prompt, respectively. In a contrastive affinity learning stage, a student model and an exponentially moving averaged teacher model are forwarded with different augmented views of the retrieved images. Teacher embeddings are enqueued into a token-specific memory. A semi-supervised contrastive loss is computed on a current batch and a contrastive affinity learning loss for student embeddings and the teacher embeddings with pseudo-labels from a affinity graph dynamically generated by semi-supervised affinity generation.
Citation
System and Method for Contrastive Affinity Learning Via Auxiliary Prompts for Generalized Novel Category Discovery, by S. Zhang, S. Khan, Z. Shen, M. Naseer, G. Chen, F. Khan. (2025, Mar. 6). Patent 20250078546 [Online]. Available: https://www.freepatentsonline.com/y2025/0078546.html
Source
US Patent App. 18/460,932, 2025
Conference
Keywords
Subjects
Source
Publisher
Google Patent