[zero-shot] uncertainty 관련 zero-shot 글들
zero-shot이란?
논문 : https://arxiv.org/abs/2011.08641
A Review of Generalized Zero-Shot Learning Methods
Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To address this challenging task, GZSL leverages semantic information of the seen
arxiv.org
zero-shot 설명
https://deep-learning-study.tistory.com/873?category=1027729
[논문 읽기] Zero-Shot Learning(ZSL) 이란?
새로운 분야 공부를 시작할 때, survey 논문을 먼저 보는 편인데 Zero shot에 흥미가 생겨서 survey 논문을 읽어봤다. Zero-Shot learning 에 대해 설명되어 있는 한국어 자료가 많이 없는 것 같아서 한번
deep-learning-study.tistory.com
Uncertainty를 이용한 응용
논문 : Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation
https://proceedings.neurips.cc/paper/2020/hash/f73b76ce8949fe29bf2a537cfa420e8f-Abstract.html
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation
Requests for name changes in the electronic proceedings will be accepted with no questions asked. However name changes may cause bibliographic tracking issues. Authors are asked to consider this carefully and discuss it with their co-authors prior to reque
proceedings.neurips.cc
위 논문에 대한 설명
https://deep-learning-study.tistory.com/884
[논문 읽기] Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation(2020)
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation PDF, Zero-Shot Segmentation, Xizhou et al, neurips 2020 Summary 논문에서 지적하는 문제점 (1) training set에 noise가 존재 왜? 이..
deep-learning-study.tistory.com