HWHui Wang

Hui Wang

*This is an algorithmically generated author record based on publicly available information.

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


Hui Wang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Unsupervised Domain Adaptation With Class-Aware Memory Alignment

    by Hui Wang, Liangli Zheng, Hanbin Zhao, Shijian Li, Xi Li

    Unsupervised domain adaptation (UDA) is to make predictions on unlabeled target domain by learning the knowledge from a label-rich source domain. In practice, existing UDA approaches mainly focus on minimizing the discrepancy between different domains by mini-batch training, where only a few instances are accessible at each iteration. Due to the randomness of sampling, such a batch-level alignment pattern is unstable and may lead to misalignment. To alleviate this risk, we propose class-aware memory alignment (CMA) that models the distributions of the two domains by two auxiliary class-aware memories and performs domain adaptation on these predefined memories. CMA is designed with two distinct characteristics: class-aware memories that create two symmetrical class-aware distributions for different domains and two reliability-based filtering strategies that enhance the reliability of the constructed memory. We further design a unified memory-based loss to jointly improve the transferability and discriminability of features in the memories. State-of-the-art (SOTA) comparisons and careful ablation studies show the effectiveness of our proposed CMA.


  • SP-Net: Slowly Progressing Dynamic Inference Networks

    by Huanyu Wang, Wenhu Zhang, Shihao Su, Hui Wang, Zhenwei Miao, Xin Zhan, Xi Li


  • Entropy-Driven Sampling and Training Scheme for Conditional Diffusion Generation

    by Guangcong Zheng, Shengming Li, Hui Wang, Taiping Yao, Yang Chen, Shouhong Ding, Xi Li


  • Epoch-Evolving Gaussian Process Guided Learning for Classification

    by Jiabao Cui, Xuewei Li, Hanbin Zhao, Hui Wang, Bin Li, Xi Li

    The conventional mini-batch gradient descent algorithms are usually trapped in the local batch-level distribution information, resulting in the ``zig-zag'' effect in the learning process. To characterize the correlation information between the batch-level distribution and the global data distribution, we propose a novel learning scheme called epoch-evolving Gaussian process guided learning (GPGL) to encode the global data distribution information in a non-parametric way. Upon a set of class-aware anchor samples, our GP model is built to estimate the class distribution for each sample in mini-batch through label propagation from the anchor samples to the batch samples. The class distribution, also named the context label, is provided as a complement for the ground-truth one-hot label. Such a class distribution structure has a smooth property and usually carries a rich body of contextual information that is capable of speeding up the convergence process. With the guidance of the context label and ground-truth label, the GPGL scheme provides a more efficient optimization through updating the model parameters with a triangle consistency loss. Furthermore, our GPGL scheme can be generalized and naturally applied to the current deep models, outperforming the state-of-the-art optimization methods on six benchmark datasets.


  • What and Where: Learn to Plug Adapters via NAS for Multidomain Learning

    by Hanbin Zhao, Hao Zeng, Xin Qin, Yongjian Fu, Hui Wang, Bourahla Omar, Xi Li

    As an important and challenging problem, multidomain learning (MDL) typically seeks a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network. Usually, existing ways of adapter plugging and structure design are handcrafted and fixed for all domains before model learning, resulting in learning inflexibility and computational intensiveness. With this motivation, we propose to learn a data-driven adapter plugging strategy with neural architecture search (NAS), which automatically determines where to plug for those adapter modules. Furthermore, we propose an NAS-adapter module for adapter structure design in an NAS-driven learning scheme, which automatically discovers effective adapter module structures for different domains. Experimental results demonstrate the effectiveness of our MDL model against existing approaches under the conditions of comparable performance.


  • Progressive Class-Based Expansion Learning for Image Classification

    by Hui Wang, Hanbin Zhao, Xi Li

    In this paper, we propose a novel image process scheme called class-based expansion learning for image classification, which aims at improving the supervision-stimulation frequency for the samples of the confusing classes. Class-based expansion learning takes a bottom-up growing strategy in a class-based expansion optimization fashion, which pays more attention to the quality of learning the fine-grained classification boundaries for the preferentially selected classes. Besides, we develop a class confusion criterion to select the confusing class preferentially for training. In this way, the classification boundaries of the confusing classes are frequently stimulated, resulting in a fine-grained form. Experimental results demonstrate the effectiveness of the proposed scheme on several benchmarks.

  • Memory-Efficient Class-Incremental Learning for Image Classification

    by Hanbin Zhao, Hui Wang, Yongjian Fu, Fei Wu, Xi Li

    With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the “catastrophic forgetting” problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples, rather than the original real-high-fidelity exemplar samples. Such a memory-efficient exemplar preserving scheme makes the old-class knowledge transfer more effective. However, the low-fidelity exemplar samples are often distributed in a different domain away from that of the original exemplar samples, that is, a domain shift. To alleviate this problem, we propose a duplet learning scheme that seeks to construct domain-compatible feature extractors and classifiers, which greatly narrows down the above domain gap. As a result, these low-fidelity auxiliary exemplar samples have the ability to moderately replace the original exemplar samples with a lower memory cost. In addition, we present a robust classifier adaptation scheme, which further refines the biased classifier (learned with the samples containing distillation label knowledge about old classes) with the help of the samples of pure true class labels. Experimental results demonstrate the effectiveness of this work against the state-of-the-art approaches. We will release the code, baselines, and training statistics for all models to facilitate future research.


  • Using Case Facts to Predict Accusation Based on Deep Learning

    by Hui Wang, Tieke He, Zhipeng Zou, Siyuan Shen, Yu Li

    Under the blessing of artificial intelligence technology, legal research is moving towards intelligent and automated. The analysis of judicial data through artificial intelligence methods has become an urgent demand. High-efficient use of data in the judiciary can reduce the burden on relevant personnel, improve the case-handling efficiency, enhance trial quality, and promote fair enforcement. In order to solve the problem of automatic sentencing in legal intelligence, this paper proposes a framework based on FastText and TextCNN to combine the deep learning with justice to predict accusation, converting accusation prediction into a multi-label text classification problem. Compared to traditional methods and machine learning models, our framework can achieve excellent performance.