CQCan Qin

Can Qin

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Can Qin has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • MuseumMaker: Continual Style Customization Without Catastrophic Forgetting

    by Chenxi Liu, Gan Sun, Wenqi Liang, Jiahua Dong, Can Qin, Yang Cong

    Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized image generation fields. However, catastrophic forgetting issue makes it hard to continually synthesize new user-provided styles while retaining the satisfying results amongst learned styles. In this paper, we propose MuseumMaker, a method that enables the synthesis of images by following a set of customized styles in a never-end manner, and gradually accumulates these creative artistic works as a Museum. When facing with a new customization style, we develop a style distillation loss module to extract and learn the styles of the training data for new image generation task. It can minimize the learning biases caused by content of new training images, and address the catastrophic overfitting issue induced by few-shot images. To deal with catastrophic forgetting issue amongst past learned styles, we devise a dual regularization for shared-LoRA module to optimize the direction of model update, which could regularize the diffusion model from both weight and feature aspects, respectively. Meanwhile, to further preserve historical knowledge from past styles and address the limited representability of LoRA, we design a task-wise token learning module where a unique token embedding is learned to denote a new style. As any new user-provided style come, our MuseumMaker can capture the nuances of the new styles while maintaining the details of learned styles. Experimental results on diverse style datasets validate the effectiveness of our proposed MuseumMaker method, showcasing its robustness and versatility across various scenarios.


  • Triple Point Masking

    by Jiaming Liu, Linghe Kong, Yue Wu, Maoguo Gong, Hao Li, Qiguang Miao, Wenping Ma, Can Qin

    Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable plug-and-play framework for MAE pre-training to achieve multi-mask learning for 3D point clouds. Specifically, we augment the baseline methods with two additional mask choices (i.e., medium mask and low mask) as our core insight is that the recovery process of an object can manifest in diverse ways. Previous high-masking schemes focus on capturing the global representation information but lack fine-grained recovery capabilities, so that the generated pre-training weights tend to play a limited role in the fine-tuning process. With the support of the proposed TPM, current methods can exhibit more flexible and accurate completion capabilities, enabling the potential autoencoder in the pre-training stage to consider multiple representations of a single 3D point cloud object. In addition, during the fine-tuning stage, an SVM-guided weight selection module is proposed to fill the encoder parameters for downstream networks with the optimal weight, maximizing linear accuracy and facilitating the acquisition of intricate representations for new objects. Extensive experimental results and theoretical analysis show that five baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks. Our code and models are available at https://github.com/liujia99/TPM.


  • SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant

    by Guohao Sun, Can Qin, Jiamian Wang, Zeyuan Chen, Ran Xu, Zhiqiang Tao


  • SLA2P: Self-Supervised Anomaly Detection With Adversarial Perturbation

    by Yizhou Wang, Can Qin, Rongzhe Wei, Yi Xu, Yue Bai, Yun Fu

    Anomaly detection is a fundational yet difficult problem in machine learning. In this work, we propose a new and effective framework, dubbed as SLA $^{2}$ P, for unsupervised anomaly detection. Following the extraction of delegate embeddings from raw data, we implement random projections on the features and consider features transformed by disparate projections as being associated with separate pseudo-classes. We then train a neural network for classification on these transformed features to conduct self-supervised learning. Subsequently, we introduce adversarial disturbances to the modified attributes, and we develop anomaly scores built on the classifier's predictive uncertainties concerning these disrupted features. Our approach is motivated by the fact that as anomalies are relatively rare and decentralized, 1) the training of the pseudo-label classifier concentrates more on acquiring the semantic knowledge of regular data instead of anomalous data; 2) the altered attributes of the normal data exhibit greater resilience to disturbances compared to those of the anomalous data. Therefore, the disrupted modified attributes of anomalies can not be well classified and correspondingly tend to attain lesser anomaly scores. The results of experiments on various benchmark datasets for images, text, and inherently tabular data demonstrate that SLA $^{2}$ P achieves state-of-the-art performance consistently.


  • Global Aligned Structured Sparsity Learning for Efficient Image Super-Resolution

    by Huan Wang, Yulun Zhang, Can Qin, Luc Van Gool, Yun Fu

    Efficient image super-resolution (SR) has witnessed rapid progress thanks to novel lightweight architectures or model compression techniques (e.g., neural architecture search and knowledge distillation). Nevertheless, these methods consume considerable resources or/and neglect to squeeze out the network redundancy at a more fine-grained convolution filter level. Network pruning is a promising alternative to overcome these shortcomings. However, structured pruning is known to be tricky when applied to SR networks because the extensive residual blocks demand the pruned indices of different layers to be the same. Besides, the principled determination of proper layerwise sparsities remains challenging too. In this article, we present Global Aligned Structured Sparsity Learning (GASSL) to resolve these problems. GASSL has two major components: Hessian-Aided Regularization (HAIR) and Aligned Structured Sparsity Learning (ASSL). HAIR is a regularization-based sparsity auto-selection algorithm with Hessian considered implicitly. A proven proposition is introduced to justify its design. ASSL is for physically pruning SR networks. Particularly, a new penalty term Sparsity Structure Alignment (SSA) is proposed to align the pruned indices of different layers. With GASSL, we design two new efficient single image SR networks of different architecture genres, pushing the efficiency envelope of SR models one step forward. Extensive results demonstrate the merits of GASSL over other recent counterparts.


  • Semi-Supervised Domain Adaptive Structure Learning

    by Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu

    Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples. In this paper, we introduce an adaptive structure learning method to regularize the cooperation of SSL and DA. Inspired by the multi-views learning, our proposed framework is composed of a shared feature encoder network and two classifier networks, trained for contradictory purposes. Among them, one of the classifiers is applied to group target features to improve intra-class density, enlarging the gap of categorical clusters for robust representation learning. Meanwhile, the other classifier, serviced as a regularizer, attempts to scatter the source features to enhance the smoothness of the decision boundary. The iterations of target clustering and source expansion make the target features being well-enclosed inside the dilated boundary of the corresponding source points. For the joint address of cross-domain features alignment and partially labeled data learning, we apply the maximum mean discrepancy (MMD) distance minimization and self-training (ST) to project the contradictory structures into a shared view to make the reliable final decision. The experimental results over the standard SSDA benchmarks, including DomainNet and Office-home, demonstrate both the accuracy and robustness of our method over the state-of-the-art approaches.


  • Generative View-Correlation Adaptation for Semi-supervised Multi-view Learning

    by Yunyu Liu, Lichen Wang, Yue Bai, Can Qin, Zhengming Ding, Yun Fu


  • Comparing sexual behaviours and knowledge between domestic students and Chinese international students in Australia: findings from two cross-sectional studies

    by Caitlin H Douglass, Can Qin, Fran Martin, Yinzong Xiao, Carol El-Hayek, Megan Sc Lim

    Few studies investigate sexual health among Chinese international students in Australia. We recruited domestic (n = 623) and Chinese international (n = 500) students for separate online surveys on sexual behaviours and knowledge. Samples were compared using Chi square, Fisher’s exact and equality of medians tests. Domestic students were more likely than international students to have ever touched a partner’s genitals (81% vs. 53%, p < 0.01), had oral sex (76% vs. 44%, p < 0.01), vaginal intercourse (67% vs. 41%, p < 0.01) and anal intercourse (31% vs. 6%, p < 0.01). Domestic students were younger when they first touched a partner’s genitals (16 vs. 18 years, p < 0.01), had oral sex (17 vs. 18 years, p < 0.01) and vaginal intercourse (17 vs. 18 years, p < 0.01). Domestic students were less likely than Chinese international students to report only one lifetime partner for touching genitals (22% vs. 50%, p < 0.01), oral sex (25% vs. 55%, p < 0.01), vaginal intercourse (30% vs. 58%, p < 0.01) and anal intercourse (54% vs. 88%, p < 0.01). Domestic students were more likely than Chinese international students to use the oral contraceptive pill (48% vs. 16%, p < 0.01) and long-acting reversible contraceptives (19% vs. 1%, p < 0.01). Domestic students scored higher than international students on a contraception and chlamydia quiz (4/5 vs. 2/5, p < 0.01). Domestic and Chinese international students differed in sexual behaviours and knowledge highlighting the need for relevant sexual health promotion for both groups.