東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Fine-grained Visual Representation Learning with Deep Neural Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Fine-grained Visual Representation Learning with Deep Neural Networks./
作者:	Xu, Tao.
面頁冊數:	1 online resource (137 pages)
附註:	Source: Dissertations Abstracts International, Volume: 80-02, Section: B.
Contained By:	Dissertations Abstracts International80-02B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10928609click for full text (PQDT)
ISBN:	9780438302396

Fine-grained Visual Representation Learning with Deep Neural Networks.
Xu, Tao.

Fine-grained Visual Representation Learning with Deep Neural Networks. - 1 online resource (137 pages)

Source: Dissertations Abstracts International, Volume: 80-02, Section: B.

Thesis (Ph.D.)--Lehigh University, 2018.

Includes bibliographical references

Representation learning is about learning representative features of the data that make it easier to extract useful information for the subsequent learning task. Due to the great success of deep learning, representations learned by deep neural networks have shown significant improvement than handcrafted features on most learning tasks. However, it is still very challenging to learn fine-grained visual representations, which refer to highly localized features extracted from images that are useful for image understanding tasks, such as fine-grained recognition, image generation and semantic segmentation. Fine-grained recognition identifies subtle visual differences to distinguish among subordinate categories; image generation learns fine-grained visual features to generate realistic details; and semantic segmentation depends on coarse-to-fine representations to segment objects with pixel-wise precision and global coherence. In this thesis, I focus on improving or extending deep neural networks to learn better fine-grained visual representations for solving those image understanding tasks. (i) Part-based fine-grained representation learning: A new Semantic Part Detection and Abstraction (SPDA) CNN architecture is proposed for fine-grained recognition. It has a detection sub-network for small semantic parts detection and a recognition sub-network to learn discriminative part-based features for fine-grained object categorization. (ii) Multimodal fine-grained representation learning: A multimodal deep learning framework is developed for fine-grained medical image classification by leveraging image and non-image clinical data collected during a patient's visit. The proposed multimodal framework learns better complementary fine-grained features from the image and non-image modalities for disease grading. (iii) Adversarial fine-grained representation learning: An Attentional Generative Adversarial Network (AttnGAN) is presented for text-to-image synthesis, while an end-to-end adversarial neural network (called SegAN) is proposed for semantic segmentation. The AttnGAN learns coarse-to-fine-grained conditions (sentence level information and word level information) to generate images with photo-realistic details. The SegAN adopts a novel adversarial critic network with a multi-scale L1 loss function to capture long- and short-range spatial relationships between pixels. Both qualitative and quantitative validation experiments are conducted for all proposed methods.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9780438302396Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deep neural networksIndex Terms--Genre/Form:

542853
Electronic books.

Fine-grained Visual Representation Learning with Deep Neural Networks.
LDR:03974nmm a2200409K 4500 001 2360472
005 20230928115644.5
006 m o d
007 cr mn ---uuuuu
008 241011s2018 xx obm 000 0 eng d
020 $a 9780438302396
035 $a (MiAaPQ)AAI10928609
035 $a (MiAaPQ)lehigh:12000
035 $a AAI10928609
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Xu, Tao. $3 1059048
245 1 0 $a Fine-grained Visual Representation Learning with Deep Neural Networks.
264 0 $c 2018
300 $a 1 online resource (137 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 80-02, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Huang, Xiaolei.
502 $a Thesis (Ph.D.)--Lehigh University, 2018.
504 $a Includes bibliographical references
520 $a Representation learning is about learning representative features of the data that make it easier to extract useful information for the subsequent learning task. Due to the great success of deep learning, representations learned by deep neural networks have shown significant improvement than handcrafted features on most learning tasks. However, it is still very challenging to learn fine-grained visual representations, which refer to highly localized features extracted from images that are useful for image understanding tasks, such as fine-grained recognition, image generation and semantic segmentation. Fine-grained recognition identifies subtle visual differences to distinguish among subordinate categories; image generation learns fine-grained visual features to generate realistic details; and semantic segmentation depends on coarse-to-fine representations to segment objects with pixel-wise precision and global coherence. In this thesis, I focus on improving or extending deep neural networks to learn better fine-grained visual representations for solving those image understanding tasks. (i) Part-based fine-grained representation learning: A new Semantic Part Detection and Abstraction (SPDA) CNN architecture is proposed for fine-grained recognition. It has a detection sub-network for small semantic parts detection and a recognition sub-network to learn discriminative part-based features for fine-grained object categorization. (ii) Multimodal fine-grained representation learning: A multimodal deep learning framework is developed for fine-grained medical image classification by leveraging image and non-image clinical data collected during a patient's visit. The proposed multimodal framework learns better complementary fine-grained features from the image and non-image modalities for disease grading. (iii) Adversarial fine-grained representation learning: An Attentional Generative Adversarial Network (AttnGAN) is presented for text-to-image synthesis, while an end-to-end adversarial neural network (called SegAN) is proposed for semantic segmentation. The AttnGAN learns coarse-to-fine-grained conditions (sentence level information and word level information) to generate images with photo-realistic details. The SegAN adopts a novel adversarial critic network with a multi-scale L1 loss function to capture long- and short-range spatial relationships between pixels. Both qualitative and quantitative validation experiments are conducted for all proposed methods.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
653 $a Deep neural networks
653 $a Fine-grained recognition
653 $a Image generation
653 $a Image understanding
653 $a Representation learning
653 $a Semantic image segmentation
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Lehigh University. $b Materials Science and Engineering. $3 1671696
773 0 $t Dissertations Abstracts International $g 80-02B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10928609 $z click for full text (PQDT)