{"product_id":"ieej-20240325c00701-008","title":"On Out-of-Domain Generalization in Semi-Supervised Pedestrian Attribute Recognition","description":"\u003cp\u003e\u003cstrong\u003eカテゴリ: \u003c\/strong\u003e研究会(論文単位)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e論文No: \u003c\/strong\u003eCMN24025\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eグループ名: \u003c\/strong\u003e【C】電子・情報・システム部門 通信研究会\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e発行日: \u003c\/strong\u003e2024\/03\/25\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eタイトル(英語): \u003c\/strong\u003eOn Out-of-Domain Generalization in Semi-Supervised Pedestrian Attribute Recognition\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名: \u003c\/strong\u003eRavikiran Manikandan(Hitachi India Pvt Ltd),Kumar Sharath(Hitachi India Pvt Ltd),Ganesh Ananth(Hitachi India Pvt Ltd)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名(英語): \u003c\/strong\u003eManikandan Ravikiran(Hitachi India Pvt Ltd),Sharath Kumar(Hitachi India Pvt Ltd),Ananth Ganesh(Hitachi India Pvt Ltd)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eキーワード: \u003c\/strong\u003eDeep Learning, |Pedestrian Attribute Recognition|Semi-supervised Learning|Deep Learning, |Pedestrian Attribute Recognition|Semi-supervised Learning\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e要約(日本語): \u003c\/strong\u003eSemi Supervised Pedestrian attribute recognition (Semi-PAR) focuses on identification of attributes of people given their input image, with less annotated samples. Recent works have shown Hierarchical Groupwise Temporal Ensemble (Hi-GOTE) based Semi-PAR improve performance over other methods by training groupwise encoders, however there is currently lack of comprehensive evaluation on out-of-domain datasets. Accordingly in this paper we empirically answer (a) How does Hi-GOTE fare against strong out-of-domain data (b) How effective Hi-GOTE is on coarse grained and fine-grained attributes (c) How does Hi-GOTE's generalization performance vary with addition of labelled samples from out-of-domain domain dataset. Empirical results against a novel out-of-domain dataset Hi-ODATA reveals that (a) Hi-GOTE's performance is on par for strong out-of-domain data (b) it performs well against coarse grained attributes and (c) addition of out-of-domain samples improves performance of Hi-GOTE by additional ~2% in accuracy. \u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e要約(英語): \u003c\/strong\u003eSemi Supervised Pedestrian attribute recognition (Semi-PAR) focuses on identification of attributes of people given their input image, with less annotated samples. Recent works have shown Hierarchical Groupwise Temporal Ensemble (Hi-GOTE) based Semi-PAR improve performance over other methods by training groupwise encoders, however there is currently lack of comprehensive evaluation on out-of-domain datasets. Accordingly in this paper we empirically answer (a) How does Hi-GOTE fare against strong out-of-domain data (b) How effective Hi-GOTE is on coarse grained and fine-grained attributes (c) How does Hi-GOTE's generalization performance vary with addition of labelled samples from out-of-domain domain dataset. Empirical results against a novel out-of-domain dataset Hi-ODATA reveals that (a) Hi-GOTE's performance is on par for strong out-of-domain data (b) it performs well against coarse grained attributes and (c) addition of out-of-domain samples improves performance of Hi-GOTE by additional ~2% in accuracy. \u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e本誌: \u003c\/strong\u003e\u003ca href=\"\/products\/ieej-20240325c00701\"\u003e2024年3月28日-2024年3月29日通信研究会\u003c\/a\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e本誌掲載ページ: \u003c\/strong\u003e43-47 p\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e原稿種別: \u003c\/strong\u003e英語\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003ePDFファイルサイズ: \u003c\/strong\u003e878 Kバイト\u003c\/p\u003e","brand":"IEEJ-P10","offers":[{"title":"冊子印刷（一般価格660円\/会員価格440円） \/ A4 \/ 5","offer_id":46352566550767,"sku":"IEEJ-20240325C00701-008-PRT","price":660.0,"currency_code":"JPY","in_stock":true},{"title":"PDFダウンロード（一般価格330円\/会員価格220円） \/ A4 \/ 5","offer_id":46355720896751,"sku":"IEEJ-20240325C00701-008-PDF","price":330.0,"currency_code":"JPY","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0718\/9512\/2159\/files\/IEEJ-KENKYUKAI_2c8607e8-5717-4caf-990e-379cfb21fffd.png?v=1743252179","url":"https:\/\/ieej.bookpark.ne.jp\/products\/ieej-20240325c00701-008","provider":"電気学会 電子図書館","version":"1.0","type":"link"}