教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2…

This document summarizes a research paper on modeling long-range dependencies in sequence data using structured state space models and deep learning. The proposed S4 model (1) derives recurrent and convolutional representations of state space models, (2) improves long-term memory using HiPPO matrices, and (3) efficiently computes state space model convolution kernels. Experiments show S4 outperfor

[sh19910711]

"解きたいタスクに有効なデータの特徴表現を擬似的なタスクを事前に解くことで獲得する / Deep Cluster: CNNの中間特徴を元にk-means + クラスタをPseudo labelとして識別 + ImageNetでの実験ではk=10000 (> 1000)が最も良い" 2018