딥러닝 기반 특징점 표현과 매칭 성능을 향상시키기 위한 트윈 네가티브 샘플링 및 쿼드 로스함수 적용 방법 및 장치
조용주, 서정일, 리한 하피스, 모흐센 알리, 아만 이샤드, 무하마드 파이살
- 11720790 (2023.08.08)
19ZR1100, 초실감 공간미디어 원천기술 개발,
- Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.
- KSP 제안 키워드
- Learning model, deep learning(DL), loss function, negative samples, training method