Learning visual representations without human supervision

Learning visual representations without human supervision

Supervised learning with deep neural networks has achieved great success in many visual recognition tasks including classification, detection, and segmentation. However, the need for expensive human annotations makes it increasingly prohibitive to embrace the massive amount of data available in the...

Saved in:

書目詳細資料
主要作者:	Xie, Jiahao
其他作者:	Chen Change Loy
格式:	Thesis-Doctor of Philosophy
語言:	English
出版:	Nanyang Technological University 2023
主題:	Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
在線閱讀:	https://hdl.handle.net/10356/171772
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

相似書籍

2D and 3D visual understanding with limited supervision
由: Wu, Zhonghua
出版: (2023)

Semi-supervised learning for visual relation annotation
由: Tajrobehkar, Mitra
出版: (2022)

Learning to control visual data translation
由: Koksal, Ali
出版: (2023)

Sparse representation for human gait recognition
由: Zeng, Zinan
出版: (2011)

Weakly-supervised learning for video understanding
由: Deng, Dingfan
出版: (2023)

Deep learning methods with less supervision
由: Chai, Youxiang
出版: (2023)

Feature representation and learning methods in visual search applications
由: Manandhar, Dipu
出版: (2019)

Towards unbiased visual language reasoning and consistent segmentation
由: Huang, Jianqiang
出版: (2023)

Instance LSeg - exploring instance level information from visual language model
由: Lin, Zixing
出版: (2023)

Reasoning over multiple human-human interaction activities
由: Perez, Mauricio Lisboa
出版: (2021)

Learning to see in the dark
由: Chen, Sihao
出版: (2021)

Skeleton-based human activity understanding
由: Liu, Jun
出版: (2019)

Skin cancer detection with deep learning
由: Gupta, Jay
出版: (2022)

Attack on training effort of deep learning
由: Ho, Tony Man Tung
出版: (2022)

Deep learning for style and domain transfer
由: Ni, Anqi
出版: (2022)

Detecting the crowdedness of people by deep learning
由: Heng, Seng En
出版: (2021)

Learning to recognize objects by adaptive knowledge transfer
由: Tao, Qingyi
出版: (2021)

Sequence-to-sequence learning for motion prediction and generation
由: Wu, Shuang
出版: (2022)

Vehicle re-identification using machine learning
由: Tang, Lisha
出版: (2022)

The augmented human - visual movement magnification
由: Tan, Ryan Jinn-En
出版: (2023)

Deep reinforcement learning for intractable routing & inverse problems
由: Zhang, Rongkai
出版: (2023)

Evaluation of adversarial attacks against deep learning models
由: Chua, Jonathan Wen Rong
出版: (2023)

The augmented human - visual movement magnification
由: Siti Nazhura Muhamad Anuar
出版: (2022)

Deep learning based car license plate recognition
由: Ngo, Jason Jun Hao
出版: (2021)

Using deep learning for quality control in cyber-manufacturing
由: Dai, Wenting
出版: (2022)

Attack on prediction confidence of deep learning neural networks
由: Ng, Garyl Xuan
出版: (2022)

A deep learning approach to image quality assessment
由: Feng, Yeli
出版: (2019)

Fine-grained image classification using deep learning
由: Sun, Deguang
出版: (2022)

Human pose estimation and action recognition based on monocular video inputs
由: Leong, Mei Chee
出版: (2020)

Image processing and machine learning for data investigation in flash memory
由: Chew, Wei Min
出版: (2023)

Evaluations of deep learning methods for detection of gap in concrete structures
由: Yang, Zhen
出版: (2021)

Concept-level image sentiment analysis with semi-supervised learning
由: Kamath, Shantanu Arun
出版: (2018)

Deep learning feature-based visual SLAM
由: Yong, Duan Kai
出版: (2023)

Typing without hands
由: Chong, Jing Hong
出版: (2023)

Human motion tracking using deep learning
由: Peok, Qing Xiang
出版: (2020)

Visual saliency computation and quality evaluation via deep learning
由: Yang, Sheng
出版: (2021)

Comparison of semi-supervised learning algorithms
由: Teo, Sheng Huai
出版: (2023)

Advanced topics in weakly supervised learning
由: Feng, Lei
出版: (2021)

Deep CNN-LSTM supervised model and CNN self-supervised model for human activity recognition
由: Liao, Zixin
出版: (2023)

Efficient learning methods for high dimensional visual data
由: Chen, Marcus Caixing
出版: (2015)