반응형

Self-supervised learning 5

[Paper review] Deep Clustering for Unsupervised Learning of Visual Features(2018)

Deep Clustering for Unsupervised Learning of Visual Features Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze, arXiv 2018 PDF, Self Supervised Learning By SeonghoonYu July 15th, 2021 Summary This paper is clustering based self-supervised learning in an offline fashion. This model jointly learns the parameters of a neural network and the cluster assignments of the resulting feature..

[Paper review] SwAV(2020), Unsupervied Learning of Visual Features by Contrasting Cluster Assignments

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments Mathilde Caron, Ishan Misra, Jullien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin arxiv 2020 PDF, Self-Supervised Learning By SeonghoonYu July 19th, 2021 Summary This paper propose an online clustering-based self-supervised method learning visual features in an online fashion without supervision Typical clusterin..

[Paper review] SeLa(2019), Self-Labelling via Simultaneous Clustering and Representation Learning

Self-Labelling via Simultaneous Clustering and Representation Learning Yuki M. Asano, Christian Rupprecht, Andrea Vedaldi arxiv 2019 PDF, Self-Supervised Learning By SeonghoonYu July 19th, 2021 Summary 신경망이 출력한 feature vector를 clustering에 할당하는데, 이 할당하는 과정을 최적 운송(optimal transport) 문제로 보고 sinkhorn algorithm으로 assignment matrix Q를 계산합니다. Q는 feature vector와 clustering의 유사도를 계산하여 clustering을 할당하는 역할..

[Paper review] BYOL(2020), Bootstrap Your Own Latent A New Approach to Self-Supervised Learning

Bootstrap Your Own Latent A New Approach to Self-Supervised Learning Jean-Bastien Grill, Florian Strub, Florent Altche, Corentin Tallec, Pierre H.Richemon, arXiv 2020 PDF, score [8/10], SSL By SeonghoonYu July 16th, 2021 Summary They suggest a new approch to self-supervised learning. (1) use two network referred to as online and target network and then update target network with a slow-moving av..

[논문 읽기] Context Prediction(2015), Unsupervised Visual Representation Learning by Context Prediction

오늘 읽은 논문은 Unsupervised Visual Representation Learning by Context Prediction 입니다. Context Prediction은 self-supervised learning이며 image로부터 patch를 추출하여 patch간의 상대적인 위치를 예측하도록 학습합니다(사람도 맞추기 어려운 task를 신경망이 prediction 하도록 합니다. 실제로 이 상대적인 위치를 예측하는 task에 대하여 학습된 ConvNet은 낮은 성능(40%)을 나타냅니다). 이 방법으로 embedding을 학습하는데, 이 embedding은 동일한 object이면 가까운 거리(유사도), 다른 object 경우에는 먼 거리를 갖도록 합니다. 이렇게 학습된 ConvNet은 tra..

반응형