Search Results 1-7 of 7

  • Few-Shot Domain Adaptation For Many Class Classification Using Commercial Products  [in Japanese]

    Takahashi Ryo , Sato Yuji , Furuyama Junko , Yamaoka Megumi , Tanabiki Masamoto , Aoki Yoshimitsu

    … <p>In order to train a classifier for self checkout system in convenience store at low cost, a few-shot domain adaptation problem has to be solved. … Since the system treats a classifier for large number of classes, conventional method of few-shot domain adaptation should be extended for many classes. …

    Journal of the Japan Society for Precision Engineering 87(1), 78-82, 2021

    J-STAGE 

  • Improved Meta-learning by Parameter Adjustment via Latent Variables and Probabilistic Inference  [in Japanese]

    SHIMIZU Eiki , AOKI Shogo , MIKAWA Kenta , GOTO Masayuki

    <p>メタ学習手法は,少数の学習データしか得られない画像分類タスクに対しても分類精度を確保できる手法として注目されている.メタ学習の代表的な手法として,Model-Agnostic Meta-Learning (以下,MAML)がある.MAMLは,タスク間に共通の初期パラメータを学習することで,データが少量のみしか存在しない新たなタスクに対しても,少ないパラメータ更新で効率的に適応する …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4I3GS202-4I3GS202, 2020

    J-STAGE 

  • Few-shot Learning with Data Augmentation with Generative Model.  [in Japanese]

    ZHOU Mu , TANIMURA Yusuke , NAKADA Hidemoto

    … <p>While deep learning, in general, requires a large amount of labeled data, there are situations where only a few samples are available for some classes. … We augment the data for the class with few samples using the generative model trained on the other classes for a classification task. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 3Rin458-3Rin458, 2020

    J-STAGE 

  • Few-shot Learning based on Prototypical Network to Understand Area Service Level in LTE Networks  [in Japanese]

    青木 章悟 , 塩本 公平 , チンラムエング , バックスタード セバスチャン

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 119(106), 151-156, 2019-07-10

  • A Model Ensemble Approach for Few-Shot Learning Using Aggregated Classifiers (Special Issue on Journal Track Papers in IEVC2019)

    KIKUCHI Toshiki , OZASA Yuko

    IIEEJ transactions on image electronics and visual computing 7(2), 97-105, 2019

  • <b>A Model Ensemble Approach for Few-Shot Learning Using Aggregated Classifiers</b>

    KIKUCHI Toshiki , OZASA Yuko

    … Previous works addressed this issue as the few-shot learning which is the task to identify the class of an example in new classes not seen in a training phase with only a few examples of each new class. … Some methods performed well on the few-shot tasks, but need a complex architecture and/or specialized loss functions, such as metric loss, meta learner, and memory. …

    IIEEJ Transactions on Image Electronics and Visual Computing 7(2), 97-105, 2019

    J-STAGE 

  • One-shot Learning using Triplet Network with kNN classifier

    ZHOU Mu , TANIMURA Yusuke , NAKADA Hidemoto

    <p>本稿では、Triplet NetworkとK近傍クラス分類器を用いたワンショット学習技術を提案する。ワンショット学習では、クラスごとに正例を1つだけあたえて訓練した学習機で対象画像のクラス分類を行う。この手法では、Tripletネットワークを用いて画像をユークリッド空間にマップし、その空間でK近傍クラス分類を行う。この際に、正例画像をデータ拡張することでワンショット学習を可能にす …

    Proceedings of the Annual Conference of JSAI JSAI2019(0), 3B3E202-3B3E202, 2019

    J-STAGE 

Page Top