HAWK-Net: Hierarchical Attention Weighted Top-K Network for High-resolution Image Classification

• Item type: Journal(1)
• 公開日: 2023-12-15
• タイトル: HAWK-Net: Hierarchical Attention Weighted Top-K Network for High-resolution Image Classification
• タイトル / 言語: en
• タイトル: HAWK-Net: Hierarchical Attention Weighted Top-K Network for High-resolution Image Classification
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [一般論文] megapixel, deep learning, attention mechanism, gated mechanism, differentiable top-K, hierarchical networks
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: The University of Tokyo
• 著者所属: The University of Tokyo
• 著者所属: The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者名: Hitoshi, Nakanishi; Masahiro, Suzuki; Yutaka, Matsuo
• 著者名(英): Hitoshi, Nakanishi; Masahiro, Suzuki; Yutaka, Matsuo
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: To handle high-resolution images on finite computational resources, many researches have been conducted on hierarchical networks to load features in only the most meaningful local regions. However, it is difficult to determine the correct number and location of patch regions at the appropriate scale in these methods. Then, incorrectly selected regions at different scales interfere with feature extraction and information integration. To solve this issue, we propose a hierarchical attention weighted network (HAWK-Net), which consists of a backbone network with differentiable Top-K selection and spatially gated blocks. The Top-K selected patches are identified from multiple image scaled features and extracted from an original high-resolution image. Then, patch features are aggregated via a novel gate mechanism under the uncertainty of the predicted information. Not only can multi-scale information uncertainty be modeled, but it also controls the gradient to the feature network coming from patch images with low confidence in the region proposal network in feedback during training. Our model is a simple yet efficient network structure that can learn from multiple scales and patches and is capable of end-to-end training. Based on benchmarks of multiple high-resolution images, our model achieves even higher performance with lower memory usage and reduced computation time.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.31(2023) (online); DOI http://dx.doi.org/10.2197/ipsjjip.31.851; ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: To handle high-resolution images on finite computational resources, many researches have been conducted on hierarchical networks to load features in only the most meaningful local regions. However, it is difficult to determine the correct number and location of patch regions at the appropriate scale in these methods. Then, incorrectly selected regions at different scales interfere with feature extraction and information integration. To solve this issue, we propose a hierarchical attention weighted network (HAWK-Net), which consists of a backbone network with differentiable Top-K selection and spatially gated blocks. The Top-K selected patches are identified from multiple image scaled features and extracted from an original high-resolution image. Then, patch features are aggregated via a novel gate mechanism under the uncertainty of the predicted information. Not only can multi-scale information uncertainty be modeled, but it also controls the gradient to the feature network coming from patch images with low confidence in the region proposal network in feedback during training. Our model is a simple yet efficient network structure that can learn from multiple scales and patches and is capable of end-to-end training. Based on benchmarks of multiple high-resolution images, our model achieves even higher performance with lower memory usage and reduced computation time.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.31(2023) (online); DOI http://dx.doi.org/10.2197/ipsjjip.31.851; ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 64, 号 12, 発行日 2023-12-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764
• 公開者 / 言語: ja
• 公開者 / 出版者: 情報処理学会