18210221. SYSTEM FOR LEARNING NEW VISUAL INSPECTION TASKS USING A FEW-SHOT META-LEARNING METHOD (Hitachi, Ltd.)

SYSTEM FOR LEARNING NEW VISUAL INSPECTION TASKS USING A FEW-SHOT META-LEARNING METHOD

Organization Name

Hitachi, Ltd.

Inventor(s)

Lasitha Sandaruwan Vidyaratne of Fremont CA (US)

Xian Yeow Lee of Santa Clara CA (US)

Mahbubul Alam of Fremont CA (US)

Ahmed Farahat of Santa Clara CA (US)

Dipanjan Ghosh of Santa Clara CA (US)

Maria Teresa Gonzalez Diaz of Mountain View CA (US)

Chetan Gupta of Sunnyvale CA (US)

SYSTEM FOR LEARNING NEW VISUAL INSPECTION TASKS USING A FEW-SHOT META-LEARNING METHOD

This abstract first appeared for US patent application 18210221 titled 'SYSTEM FOR LEARNING NEW VISUAL INSPECTION TASKS USING A FEW-SHOT META-LEARNING METHOD

Original Abstract Submitted

Systems and methods described herein which can involve for a first input of a plurality of labeled images of a new domain task, processing the first plurality of labeled images through a plurality of backbone snapshots, each of the backbone snapshots representative of a model trained across a plurality of other domain tasks, each of the plurality of backbone snapshots configured to output a first plurality of features responsive to the input; processing a second input of second plurality of unlabeled images through the plurality of backbone snapshots to output a second plurality of features responsive to the second input; and generating a representative model for the new domain task from the clustering and transformation of the first plurality of features and as associated from the clustered and transformed second plurality of features.