목록Experiences & Study/Paper (ETC) (3)
On the journey of
[논문읽기] CLIP : Learning Transferable Visual Models From Natural Language Supervision
Multi-Modal 및 NLP, Multi task 관련 논문작업을 시작할 수도 있어서 (자세한 설명은 생략) 멀티모달 관련 공부를 시작했다. 멀티모달 같은 경우 처음은 아니지만 경험이 많은 건 더더욱 아니라서 ^.^ CV와 함께 공부해야 할 것 같다 :-) Original Paper ) https://arxiv.org/abs/2103.00020 Learning Transferable Visual Models From Natural Language Supervision State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form..
[논문읽기] Self-training with Noisy Student improves ImageNet classification
Original Paper ) https://arxiv.org/abs/1911.04252 Self-training with Noisy Student improves ImageNet classification We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires arxiv.org Situation and Pr..
[논문읽기] Deep One-class classification(2018) & PyTORCH 코드
Original Paper ) https://proceedings.mlr.press/v80/ruff18a.html Deep One-Class Classification Despite the great advances made by deep learning in many machine learning problems, there is a relative dearth of deep learning approaches for anomaly detection. Those approaches which do exist inv... proceedings.mlr.press * Explainable Deep one-class classification 논문(2020)도 존재하기 때문에 구분할 필요가 있다. 1. Mot..