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
Pengesan objek berprestasi tinggi terkini biasanya bergantung pada pendekatan dua peringkat, yang mendapat manfaat daripada cadangan wilayah dan amalan penapisan tetapi mengalami kelajuan pengesanan yang rendah. Sebaliknya, pendekatan satu peringkat mempunyai kelebihan kecekapan tinggi sambil mengorbankan ketepatannya sedikit sebanyak. Dalam makalah ini, kami mencadangkan rangkaian pengesanan objek tangkapan tunggal novel yang mewarisi merit kedua-duanya. Didorong oleh idea pengayaan semantik kepada ciri konvolusi dalam pengesan dalam biasa, kami mencadangkan dua modul baru: 1) dengan memodelkan interaksi semantik antara saluran dan kebergantungan jarak jauh antara kedudukan spatial, modul hadir sendiri menjana kedua-dua saluran dan meletakkan perhatian, dan meningkatkan ciri konvolusi asal dengan cara berpandu sendiri; 2) memanfaatkan keupayaan penyetempatan diskriminatif kelas CNN terlatih klasifikasi, modul pengaktifan semantik mempelajari tindak balas konvolusi bermakna semantik yang menambah ciri konvolusi peringkat rendah dengan maklumat semantik khusus kelas yang kukuh. Rangkaian pengaktifan semantik dan hadir sendiri (ASAN) mencapai ketepatan yang lebih baik daripada kaedah dua peringkat dan mampu memenuhi pemprosesan masa nyata. Eksperimen komprehensif pada PASCAL VOC menunjukkan bahawa ASAN mencapai prestasi pengesanan terkini dengan kecekapan tinggi.
Xinyu ZHU
Fudan University
Jun ZHANG
Fudan University
Gengsheng CHEN
Fudan University
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
Xinyu ZHU, Jun ZHANG, Gengsheng CHEN, "ASAN: Self-Attending and Semantic Activating Network towards Better Object Detection" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 3, pp. 648-659, March 2020, doi: 10.1587/transinf.2019EDP7164.
Abstract: Recent top-performing object detectors usually depend on a two-stage approach, which benefits from its region proposal and refining practice but suffers low detection speed. By contrast, one-stage approaches have the advantage of high efficiency while sacrifice their accuracies to some extent. In this paper, we propose a novel single-shot object detection network which inherits the merits of both. Motivated by the idea of semantic enrichment to the convolutional features within a typical deep detector, we propose two novel modules: 1) by modeling the semantic interactions between channels and the long-range dependencies between spatial positions, the self-attending module generates both channel and position attention, and enhance the original convolutional features in a self-guided manner; 2) leveraging the class-discriminative localization ability of classification-trained CNN, the semantic activating module learns a semantic meaningful convolutional response which augments low-level convolutional features with strong class-specific semantic information. The so called self-attending and semantic activating network (ASAN) achieves better accuracy than two-stage methods and is able to fulfil real-time processing. Comprehensive experiments on PASCAL VOC indicates that ASAN achieves state-of-the-art detection performance with high efficiency.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7164/_p
Salinan
@ARTICLE{e103-d_3_648,
author={Xinyu ZHU, Jun ZHANG, Gengsheng CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={ASAN: Self-Attending and Semantic Activating Network towards Better Object Detection},
year={2020},
volume={E103-D},
number={3},
pages={648-659},
abstract={Recent top-performing object detectors usually depend on a two-stage approach, which benefits from its region proposal and refining practice but suffers low detection speed. By contrast, one-stage approaches have the advantage of high efficiency while sacrifice their accuracies to some extent. In this paper, we propose a novel single-shot object detection network which inherits the merits of both. Motivated by the idea of semantic enrichment to the convolutional features within a typical deep detector, we propose two novel modules: 1) by modeling the semantic interactions between channels and the long-range dependencies between spatial positions, the self-attending module generates both channel and position attention, and enhance the original convolutional features in a self-guided manner; 2) leveraging the class-discriminative localization ability of classification-trained CNN, the semantic activating module learns a semantic meaningful convolutional response which augments low-level convolutional features with strong class-specific semantic information. The so called self-attending and semantic activating network (ASAN) achieves better accuracy than two-stage methods and is able to fulfil real-time processing. Comprehensive experiments on PASCAL VOC indicates that ASAN achieves state-of-the-art detection performance with high efficiency.},
keywords={},
doi={10.1587/transinf.2019EDP7164},
ISSN={1745-1361},
month={March},}
Salinan
TY - JOUR
TI - ASAN: Self-Attending and Semantic Activating Network towards Better Object Detection
T2 - IEICE TRANSACTIONS on Information
SP - 648
EP - 659
AU - Xinyu ZHU
AU - Jun ZHANG
AU - Gengsheng CHEN
PY - 2020
DO - 10.1587/transinf.2019EDP7164
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2020
AB - Recent top-performing object detectors usually depend on a two-stage approach, which benefits from its region proposal and refining practice but suffers low detection speed. By contrast, one-stage approaches have the advantage of high efficiency while sacrifice their accuracies to some extent. In this paper, we propose a novel single-shot object detection network which inherits the merits of both. Motivated by the idea of semantic enrichment to the convolutional features within a typical deep detector, we propose two novel modules: 1) by modeling the semantic interactions between channels and the long-range dependencies between spatial positions, the self-attending module generates both channel and position attention, and enhance the original convolutional features in a self-guided manner; 2) leveraging the class-discriminative localization ability of classification-trained CNN, the semantic activating module learns a semantic meaningful convolutional response which augments low-level convolutional features with strong class-specific semantic information. The so called self-attending and semantic activating network (ASAN) achieves better accuracy than two-stage methods and is able to fulfil real-time processing. Comprehensive experiments on PASCAL VOC indicates that ASAN achieves state-of-the-art detection performance with high efficiency.
ER -