Zero-Shot Learning via Structure-Aligned Generative Adversarial Network

Tang, Chenwei; He, Zhenan; Li, Yunxia; Lv, Jiancheng

doi:10.1109/tnnls.2021.3083367

Cited by 21 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Driven by zero-shot learning (ZSL) research (Mishra et al 2018;Tang et al 2019;Jasani and Mazagonwalla 2019;Demirel, Cinbis, and Ikizler-Cinbis 2019;Tang et al 2020Tang et al , 2021, which transfers knowledge from seen to unseen classes, the challenging task of zero-shot detection (ZSD) has gained attention since its introduction in 2018 (Bansal et al 2018)…”

Section: Related Workmentioning

confidence: 99%

Zero-Shot Aerial Object Detection with Visual Description Regularization

Zang,

Lin,

Tang

et al. 2024

AAAI

View full text Add to dashboard Cite

Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to study label-efficient object detection methods on aerial images. In this work, we propose a zero-shot method for aerial object detection named visual Description Regularization, or DescReg. Concretely, we identify the weak semantic-visual correlation of the aerial objects and aim to address the challenge with prior descriptions of their visual appearance. Instead of directly encoding the descriptions into class embedding space which suffers from the representation gap problem, we propose to infuse the prior inter-class visual similarity conveyed in the descriptions into the embedding learning. The infusion process is accomplished with a newly designed similarity-aware triplet loss which incorporates structured regularization on the representation space. We conduct extensive experiments with three challenging aerial object detection datasets, including DIOR, xView, and DOTA. The results demonstrate that DescReg significantly outperforms the state-of-the-art ZSD methods with complex projection designs and generative frameworks, e.g., DescReg outperforms best reported ZSD method on DIOR by 4.5 mAP on unseen classes and 8.1 in HM. We further show the generalizability of DescReg by integrating it into generative ZSD methods as well as varying the detection architecture. Codes will be released at https://github.com/zq-zang/DescReg.

show abstract

Section: Related Workmentioning

confidence: 99%

Zero-Shot Aerial Object Detection with Visual Description Regularization

Zang,

Lin,

Tang

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…In the generative modeling, we estimate the density 𝑝(𝑥) of the observed data (𝑥) [14,15]. Currently, various studies are being actively conducted on generative models based on statistics and machine learning [16][17][18][19][20][21][22]. In the field of biology, single-cell genomic data also take the form of large count matrices characterized by a high occurrence of zeros.…”

Section: Generative Modelingmentioning

confidence: 99%

Keyword Data Analysis Using Generative Models Based on Statistics and Machine Learning Algorithms

Jun

2024

Electronics

View full text Add to dashboard Cite

For text big data analysis, we preprocessed text data and constructed a document–keyword matrix. The elements of this matrix represent the frequencies of keywords occurring in a document. The matrix has a zero-inflation problem because many elements are zero values. Also, in the process of preprocessing, the data size of the document–keyword matrix is reduced. However, various machine learning algorithms require a large amount of data, so to solve the problems of data shortage and zero inflation, we propose the use of generative models based on statistics and machine learning. In our experimental tests, we compared the performance of the models using simulation and practical data sets. Thus, we verified the validity and contribution of our research for keyword data analysis.

show abstract

“…In addition, DL is difficult to be applied to small-scale, multidimensional, and heterogeneous molecular imaging data. Recently, the proposals of small-sample learning and transfer learning make DL technologies achieve good results in the field of nuclear medicine [85,[88][89][90] . DL methods can be used to realize the image reconstruction, denoising, segmentation, and fusion of molecular imaging.…”

Section: Data Types In Nuclear Industry Chainmentioning

confidence: 99%

“…Moreover, the amount of data required for the DNNs training is large, but the cost of obtaining and labeling training data samples is very high, especially in special scenarios, e.g., the nuclear industry. The proposals of small-sample learning, fewshot learning, and zero-shot learning [88,145,146] enable the neural network model to obtain a learning ability of knowledge transfer after learning a small amount of data. In addition, the proposals of incremental learning [147] allow the neural network models to have the ability to continuously acquire and adjust, as well as learn novel data, so as to realize the dynamic change ability of the model to deal with environmental changes.…”

Section: Future Of Intelligent Nuclear Industrymentioning

confidence: 99%

Deep learning in nuclear industry: A survey

Tang

Gao

et al. 2022

Big Data Min. Anal.

Self Cite

View full text Add to dashboard Cite

As a high-tech strategic emerging comprehensive industry, the nuclear industry is committed to the research, production, and processing of nuclear fuel, as well as the development and utilization of nuclear energy.Nowadays, the nuclear industry has made remarkable progress in the application fields of nuclear weapons, nuclear power, nuclear medical treatment, radiation processing, and so on. With the development of artificial intelligence and the proposal of "Industry 4.0", more and more artificial intelligence technologies are introduced into the nuclear industry chain to improve production efficiency, reduce operation cost, improve operation safety, and realize risk avoidance. Meanwhile, deep learning, as an important technology of artificial intelligence, has made amazing progress in theoretical and applied research in the nuclear industry, which vigorously promotes the development of informatization, digitization, and intelligence of the nuclear industry. In this paper, we first simply comb and analyze the intelligent demand scenarios in the whole industrial chain of the nuclear industry. Then, we discuss the data types involved in the nuclear industry chain. After that, we investigate the research status of deep learning in the application fields corresponding to different data types in the nuclear industry. Finally, we discuss the limitation and unique challenges of deep learning in the nuclear industry and the future direction of the intelligent nuclear industry.

show abstract

Zero-Shot Learning via Structure-Aligned Generative Adversarial Network

Cited by 21 publications

References 39 publications

Zero-Shot Aerial Object Detection with Visual Description Regularization

Zero-Shot Aerial Object Detection with Visual Description Regularization

Keyword Data Analysis Using Generative Models Based on Statistics and Machine Learning Algorithms

Deep learning in nuclear industry: A survey

Contact Info

Product

Resources

About