Lg Electronics Inc.

University of Toronto

Jongseong Jang

Hyunwoo Kim

Dongsub Shim

Jihwan Jeong

Scott Sanner

Zheda Mai

A method for scoring training data samples according to an ability to preserve latent decision boundaries for previously observed classes while promoting learning from an input batch of new images from an online data stream, comprising: receiving the input batch of the new images from the online data stream, performing a memory retrieval process that retrieves data to be learned along with a new set of data from the memory to retain the previously learned knowledge, and performing a memory update process that selects and exchanges a small set of data to be saved in the memory in the memory update process. In addition, the method performs data valuation based on KNN-SV for both the memory retrieval and memory update processes to perform strategic and intuitive data selection based on the properties of KNN-SV.

Growing community of inventors

Hanam-si, South Korea

Jongseong Jang