引き続き論文《FastReID:A Pytorch Toolbox for Real-world Person Re-identification》と《Deep Learning for Person Re-identification: A Survey and Outlook》。前者は主にそのネットワーク構築を学び、関連コードを読む。後者は更にこの課題を全面的に理解する以外に、この文章の中に少なくとも二つの観点がめって、思考に値します。第一に、新しい評価指標mINPの提出、第二にReIDをClosed-world と Open-worldに分けて、実際の応用から論証と研究を行います。
After reading some paper, I find that most paper are depth-supervised or a combination of depth, pose and stereo. And I don't find any paper only using pose-supervised.
The reason why not only using pose-supervised is that only considering large intensity gradient area will produce better results. And area with less texture will cause … Continue Reading ››
引き続き論文《Deep Learning for Person Re-identification: A Survey and Outlook》と《Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking 》、勉強しながら基礎知識を整理する。
顔認識(Face recognition )は、以前出会ったdlib問題を解決しました。
2020年5月、つまり先月末、JD AI Research学術界と工業界に向けたReID Toolbox –FastReIDを公開したばかりです。(概要、FastReID provides a complete toolkit for training, evaluation, finetuning and model deployment. Besides, FastReID provides strong baselines that are capable of achieving state-of-the-art performance on multiple … Continue Reading ››
reproduce the code of paper(DepthNet), and upload to https://mountain.elcs.kyutech.ac.jp/zhou/convlstm.git
problems: there is no stride in FC_LSTM and LSTM, but it exist in CNN. I used interpolation to process C of pre_layer, but it may not be the best method. Maybe this is a point that can be improved in the future.