The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Pembelajaran sifar pukulan (ZSL) bertujuan untuk mengklasifikasikan imej kelas ghaib dengan mempelajari hubungan antara ciri visual dan semantik. Kerja sedia ada telah meningkatkan ketepatan pengecaman daripada pelbagai pendekatan, tetapi mereka menggunakan algoritma intensif pengiraan yang memerlukan pengoptimuman berulang. Dalam kerja ini, kami menyemak semula pendekatan utama pengecaman corak, iaitu, pengelas jiran terdekat, untuk menyelesaikan tugas ZSL dengan cara yang sangat mudah dan pantas, dipanggil SimpleZSL. Algoritma kami terdiri daripada tiga teknik mudah berikut: (1) hanya purata vektor ciri untuk mendapatkan prototaip visual kelas yang dilihat, (2) mengira matriks songsang pseudo melalui penguraian nilai tunggal untuk menjana ciri visual kelas yang tidak kelihatan, dan (3) membuat kesimpulan kelas ghaib oleh pengelas jiran terdekat di mana persamaan kosinus digunakan untuk mengukur jarak antara vektor ciri. Melalui eksperimen pada set data biasa, kaedah yang dicadangkan mencapai ketepatan pengiktirafan yang baik dengan kos pengiraan yang sangat kecil. Masa pelaksanaan kaedah yang dicadangkan pada CPU tunggal adalah lebih daripada 100 kali lebih cepat daripada pelaksanaan GPU kaedah sedia ada dengan ketepatan yang setanding.
Masayuki HIROMOTO
Fujitsu Limited
Hisanao AKIMA
Fujitsu Limited
Teruo ISHIHARA
Fujitsu Limited
Takuji YAMAMOTO
Fujitsu Limited
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Masayuki HIROMOTO, Hisanao AKIMA, Teruo ISHIHARA, Takuji YAMAMOTO, "SimpleZSL: Extremely Simple and Fast Zero-Shot Learning with Nearest Neighbor Classifiers" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 2, pp. 396-405, February 2022, doi: 10.1587/transinf.2021EDP7089.
Abstract: Zero-shot learning (ZSL) aims to classify images of unseen classes by learning relationship between visual and semantic features. Existing works have been improving recognition accuracy from various approaches, but they employ computationally intensive algorithms that require iterative optimization. In this work, we revisit the primary approach of the pattern recognition, ı.e., nearest neighbor classifiers, to solve the ZSL task by an extremely simple and fast way, called SimpleZSL. Our algorithm consists of the following three simple techniques: (1) just averaging feature vectors to obtain visual prototypes of seen classes, (2) calculating a pseudo-inverse matrix via singular value decomposition to generate visual features of unseen classes, and (3) inferring unseen classes by a nearest neighbor classifier in which cosine similarity is used to measure distance between feature vectors. Through the experiments on common datasets, the proposed method achieves good recognition accuracy with drastically small computational costs. The execution time of the proposed method on a single CPU is more than 100 times faster than those of the GPU implementations of the existing methods with comparable accuracies.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7089/_p
Salinan
@ARTICLE{e105-d_2_396,
author={Masayuki HIROMOTO, Hisanao AKIMA, Teruo ISHIHARA, Takuji YAMAMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={SimpleZSL: Extremely Simple and Fast Zero-Shot Learning with Nearest Neighbor Classifiers},
year={2022},
volume={E105-D},
number={2},
pages={396-405},
abstract={Zero-shot learning (ZSL) aims to classify images of unseen classes by learning relationship between visual and semantic features. Existing works have been improving recognition accuracy from various approaches, but they employ computationally intensive algorithms that require iterative optimization. In this work, we revisit the primary approach of the pattern recognition, ı.e., nearest neighbor classifiers, to solve the ZSL task by an extremely simple and fast way, called SimpleZSL. Our algorithm consists of the following three simple techniques: (1) just averaging feature vectors to obtain visual prototypes of seen classes, (2) calculating a pseudo-inverse matrix via singular value decomposition to generate visual features of unseen classes, and (3) inferring unseen classes by a nearest neighbor classifier in which cosine similarity is used to measure distance between feature vectors. Through the experiments on common datasets, the proposed method achieves good recognition accuracy with drastically small computational costs. The execution time of the proposed method on a single CPU is more than 100 times faster than those of the GPU implementations of the existing methods with comparable accuracies.},
keywords={},
doi={10.1587/transinf.2021EDP7089},
ISSN={1745-1361},
month={February},}
Salinan
TY - JOUR
TI - SimpleZSL: Extremely Simple and Fast Zero-Shot Learning with Nearest Neighbor Classifiers
T2 - IEICE TRANSACTIONS on Information
SP - 396
EP - 405
AU - Masayuki HIROMOTO
AU - Hisanao AKIMA
AU - Teruo ISHIHARA
AU - Takuji YAMAMOTO
PY - 2022
DO - 10.1587/transinf.2021EDP7089
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2022
AB - Zero-shot learning (ZSL) aims to classify images of unseen classes by learning relationship between visual and semantic features. Existing works have been improving recognition accuracy from various approaches, but they employ computationally intensive algorithms that require iterative optimization. In this work, we revisit the primary approach of the pattern recognition, ı.e., nearest neighbor classifiers, to solve the ZSL task by an extremely simple and fast way, called SimpleZSL. Our algorithm consists of the following three simple techniques: (1) just averaging feature vectors to obtain visual prototypes of seen classes, (2) calculating a pseudo-inverse matrix via singular value decomposition to generate visual features of unseen classes, and (3) inferring unseen classes by a nearest neighbor classifier in which cosine similarity is used to measure distance between feature vectors. Through the experiments on common datasets, the proposed method achieves good recognition accuracy with drastically small computational costs. The execution time of the proposed method on a single CPU is more than 100 times faster than those of the GPU implementations of the existing methods with comparable accuracies.
ER -