Haohan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Haohan Wang has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Haoqian Wang
Tsinghua University, Shenzhen, China
2 shared publications - Jingjing Lv
JD.com, Beijing, China
2 shared publications - Wei Feng
JD.com, Beijing, China
2 shared publications - Weizhen Wang
JD.com, Beijing, China
2 shared publications - Zhuoling Li
University of Hong Kong, Hong Kong
2 shared publications - Bing Zhan
NLPR & MAIS, CASIA, Beijing, China and School of AI, UCAS, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3397-3408
One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3397-3408
Open AccessOne Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2262-2275
CTR-Driven Advertising Image Generation with Multimodal Large Language Models
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2262-2275
Open AccessCTR-Driven Advertising Image Generation with Multimodal Large Language Models
- Open Access
Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
Data augmentation has been proven to be an effective technique for developing machine learning models that are robust to known classes of distributional shifts (e.g., rotations of images), and alignment regularization is a technique often used together with data augmentation to further help the model learn representations invariant to the shifts used to augment the data. In this paper, motivated by a proliferation of options of alignment regularizations, we seek to evaluate the performances of several popular design choices along the dimensions of robustness and invariance, for which we introduce a new test procedure. Our synthetic experiment results speak to the benefits of squared l2 norm regularization. Further, we also formally analyze the behavior of alignment regularization to complement our empirical study under assumptions we consider realistic. Finally, we test this simple technique we identify (worst-case data augmentation with squared l2 norm alignment regularization) and show that the benefits of this method outrun those of the specially designed methods. We also release a software package in both TensorFlow and PyTorch for users to use the method with a couple of lines at https://github.com/jyanln/AlignReg.
Open AccessToward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
Data augmentation has been proven to be an effective technique for developing machine learning models that are robust to known classes of distributional shifts (e.g., rotations of images), and alignment regularization is a technique often used together with data augmentation to further help the model learn representations invariant to the shifts used to augment the data. In this paper, motivated by a proliferation of options of alignment regularizations, we seek to evaluate the performances of several popular design choices along the dimensions of robustness and invariance, for which we introduce a new test procedure. Our synthetic experiment results speak to the benefits of squared l2 norm regularization. Further, we also formally analyze the behavior of alignment regularization to complement our empirical study under assumptions we consider realistic. Finally, we test this simple technique we identify (worst-case data augmentation with squared l2 norm alignment regularization) and show that the benefits of this method outrun those of the specially designed methods. We also release a software package in both TensorFlow and PyTorch for users to use the method with a couple of lines at https://github.com/jyanln/AlignReg.
- 26 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 4 (3) , 522-533
Efficient Few-Shot Classification via Contrastive Pretraining on Web Data
Few-shot classification is challenging due to the limited data and labels. Existing algorithms usually resolve this problem by pre-training models with a considerable amount of annotated data which shares knowledge with the target domain. Nevertheless, large quantities of homogenous data samples are not always available. To tackle this obstacle, we develop a few-shot learning framework that prepares data automatically and still produces well-behaved models. This framework is implemented through conducting contrastive learning on unlabeled web images. Instead of requiring manually annotated data, this framework trains models via constructing pseudo labels. Additionally, since online data is virtually limitless and continues to be generated, the model can thus be empowered to constantly obtain up-to-date knowledge from the Internet. Furthermore, we observe that the generalization ability of learned representation is crucial for self-supervised learning. To present its importance, a naive yet efficient normalization strategy is proposed. Consequentially, this strategy boosts the accuracy of trained models significantly. We demonstrate the superiority of the proposed framework with experiments on miniImageNet, tieredImageNet and Omniglot. The results indicate that our method has surpassed previous unsupervised counterparts by a large margin and obtained performance comparable with some supervised ones.
- 26 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 4 (3) , 522-533
Efficient Few-Shot Classification via Contrastive Pretraining on Web Data
Few-shot classification is challenging due to the limited data and labels. Existing algorithms usually resolve this problem by pre-training models with a considerable amount of annotated data which shares knowledge with the target domain. Nevertheless, large quantities of homogenous data samples are not always available. To tackle this obstacle, we develop a few-shot learning framework that prepares data automatically and still produces well-behaved models. This framework is implemented through conducting contrastive learning on unlabeled web images. Instead of requiring manually annotated data, this framework trains models via constructing pseudo labels. Additionally, since online data is virtually limitless and continues to be generated, the model can thus be empowered to constantly obtain up-to-date knowledge from the Internet. Furthermore, we observe that the generalization ability of learned representation is crucial for self-supervised learning. To present its importance, a naive yet efficient normalization strategy is proposed. Consequentially, this strategy boosts the accuracy of trained models significantly. We demonstrate the superiority of the proposed framework with experiments on miniImageNet, tieredImageNet and Omniglot. The results indicate that our method has surpassed previous unsupervised counterparts by a large margin and obtained performance comparable with some supervised ones.
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-12
Few-Shot Steel Surface Defect Detection
Deep learning based algorithms have been widely employed to build reliable steel surface defect detection systems, which are important for manufacturing. The performance of deep learning models relies heavily on abundant annotated data. Nevertheless, the labeled image volume in industrial datasets is often limited. The scarcity of training data would lead to poor detection precision. To tackle this issue, we propose the first few-shot defect detection framework. Through pre-training models using data relevant to the target task, the proposed framework can produce well-trained networks with a few labeled images. Meanwhile, we release the first publicly available few-shot defect detection dataset, namely few-shot NEU-DET (FS-ND). This dataset will serve as a fair benchmark for contrasting various methods. Afterwards, we analyze the characteristics of steel surface defect detection. It is observed that the limited amount of training data can hardly cover the data distributions in practical applications. Given this observation, we develop two domain generalization strategies that enhance the appearance and scale diversity of extracted features. Furthermore, it is found that noise existing in industrial images could result in the collapse of models. To address this problem, we devise a noise regularization strategy that improves the robustness of trained models significantly. We have conducted extensive experiments to evaluate the effectiveness of our framework. The results indicate that our framework outperforms the contrasted baseline by around 15 mAP and achieves comparable performance with models trained using abundant data.
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-12
Few-Shot Steel Surface Defect Detection
Deep learning based algorithms have been widely employed to build reliable steel surface defect detection systems, which are important for manufacturing. The performance of deep learning models relies heavily on abundant annotated data. Nevertheless, the labeled image volume in industrial datasets is often limited. The scarcity of training data would lead to poor detection precision. To tackle this issue, we propose the first few-shot defect detection framework. Through pre-training models using data relevant to the target task, the proposed framework can produce well-trained networks with a few labeled images. Meanwhile, we release the first publicly available few-shot defect detection dataset, namely few-shot NEU-DET (FS-ND). This dataset will serve as a fair benchmark for contrasting various methods. Afterwards, we analyze the characteristics of steel surface defect detection. It is observed that the limited amount of training data can hardly cover the data distributions in practical applications. Given this observation, we develop two domain generalization strategies that enhance the appearance and scale diversity of extracted features. Furthermore, it is found that noise existing in industrial images could result in the collapse of models. To address this problem, we devise a noise regularization strategy that improves the robustness of trained models significantly. We have conducted extensive experiments to evaluate the effectiveness of our framework. The results indicate that our framework outperforms the contrasted baseline by around 15 mAP and achieves comparable performance with models trained using abundant data.