Author name cluster

Houcheng Su

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

IJCAI Conference 2025 Conference Paper

ESBN: Estimation Shift of Batch Normalization for Source-free Universal Domain Adaptation

Jiao Li
Houcheng Su
Bingli Wang
Yuandong Min
Mengzhu Wang
Nan Yin
Shanshan Wang
Jingcai Guo

Domain adaptation (DA) is crucial for transferring models trained in one domain to perform well in a different, often unseen domain. Traditional methods, including unsupervised domain adaptation (UDA) and source-free domain adaptation (SFDA), have made significant progress. However, most existing DA methods rely heavily on Batch Normalization (BN) layers, which are not optimal in source-free settings, where the source domain is unavailable for comparison. In this study, we propose a novel method, ESBN, which addresses the challenge of domain shift by adjusting the placement of normalization layers and replacing BN with Batch-free Normalization (BFN). Unlike BN, BFN is less dependent on batch statistics and provides more robust feature representations through instance-specific statistics. We systematically investigate the effects of different BN layer placements across various network configurations and demonstrate that selective replacement with BFN improves generalization performance. Extensive experiments on multiple domain adaptation benchmarks show that our approach outperforms state-of-the-art methods, particularly in challenging scenarios such as Open-Partial Domain Adaptation (OPDA).

PDF Details DOI

ICML Conference 2025 Conference Paper

GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation

Mengzhu Wang
Houcheng Su
Jiao Li
Chuan Li
Nan Yin
Li Shen 0008
Jingcai Guo

Semi-supervised learning (SSL) has made notable advancements in medical image segmentation (MIS), particularly in scenarios with limited labeled data and significantly enhancing data utilization efficiency. Previous methods primarily focus on complex training strategies to utilize unlabeled data but neglect the importance of graph structural information. Different from existing methods, we propose a graph-based clustering for semi-supervised medical image segmentation (GraphCL) by jointly modeling graph data structure in a unified deep model. The proposed GraphCL model enjoys several advantages. Firstly, to the best of our knowledge, this is the first work to model the data structure information for semi-supervised medical image segmentation (SSMIS). Secondly, to get the clustered features across different graphs, we integrate both pairwise affinities between local image features and raw features as inputs. Extensive experimental results on three standard benchmarks show that the proposed GraphCL algorithm outperforms state-of-the-art semi-supervised medical image segmentation methods.

Details

EAAI Journal 2025 Journal Article

Sharpness-aware multidomain imbalance generalization with external adversarial learning and intrinsic balanced entropy regularization for intelligent fault diagnosis

Shuaiqing Deng
Zihao Lei
Guangrui Wen
Yu Su
Zhifen Zhang
Houcheng Su
Xuefeng Chen
Chunsheng Yang

In practical industrial scenarios, due to the diversity of operating conditions and the complexity of equipment operations, target condition data are often difficult to obtain. Moreover, mechanical faults occur sporadically and unpredictably, leading to complex class imbalance and domain imbalance phenomena in data across different conditions. The coupling of source domain data imbalance and target condition unknowability forms an imbalance domain generalization (IDG) problem, severely limiting the accuracy and industrial application of intelligent fault diagnosis models. To address this, this paper proposes a sharpness-aware multidomain imbalance generalization method, incorporating external adversarial learning and intrinsic balanced entropy regularization, to construct a class-unbiased and domain-invariant intelligent fault diagnosis model. Specifically, a novel spatiotemporal feature extraction module is designed to achieve an efficient fusion of multi-order spatial and multi-channel features, significantly enhancing the model's feature extraction capability. Subsequently, through the joint domain generalization with the balanced regularization approach, the model aligns the marginal and conditional probabilities across domains under data imbalance conditions, effectively mitigating the negative impact of data imbalance. Finally, the sharpness-aware minimization training strategy is employed to optimize the loss landscape during IDG, further improving the model's generalization performance. Experimental results on four typical IDG engineering scenarios and various imbalance degrees demonstrate that the proposed method achieves state-of-the-art performance, highlighting its significant advantages and application potential in addressing IDG engineering problems.

Details DOI

AAAI Conference 2024 Conference Paper

Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization

Houcheng Su
Weihao Luo
Daixian Liu
Mengzhu Wang
Jing Tang
Junyang Chen
Cong Wang
Zhenghan Chen

Domain Generalization (DG) aims to improve the generalization ability of models trained on a specific group of source domains, enabling them to perform well on new, unseen target domains. Recent studies have shown that methods that converge to smooth optima can enhance the generalization performance of supervised learning tasks such as classification. In this study, we examine the impact of smoothness-enhancing formulations on domain adversarial training, which combines task loss and adversarial loss objectives. Our approach leverages the fact that converging to a smooth minimum with respect to task loss can stabilize the task loss and lead to better performance on unseen domains. Furthermore, we recognize that the distribution of objects in the real world often follows a long-tailed class distribution, resulting in a mismatch between machine learning models and our expectations of their performance on all classes of datasets with long-tailed class distributions. To address this issue, we consider the domain generalization problem from the perspective of the long-tail distribution and propose using the maximum square loss to balance different classes which can improve model generalizability. Our method's effectiveness is demonstrated through comparisons with state-of-the-art methods on various domain generalization datasets. Code: https://github.com/bamboosir920/SAMALTDG.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Sparse Enhanced Network: An Adversarial Generation Method for Robust Augmentation in Sequential Recommendation

Junyang Chen
Guoxuan Zou
Pan Zhou
Wu Yirui
Zhenghan Chen
Houcheng Su
Huan Wang
Zhiguo Gong

Sequential Recommendation plays a significant role in daily recommendation systems, such as e-commerce platforms like Amazon and Taobao. However, even with the advent of large models, these platforms often face sparse issues in the historical browsing records of individual users due to new users joining or the introduction of new products. As a result, existing sequence recommendation algorithms may not perform well. To address this, sequence-based data augmentation methods have garnered attention. Existing sequence enhancement methods typically rely on augmenting existing data, employing techniques like cropping, masking prediction, random reordering, and random replacement of the original sequence. While these methods have shown improvements, they often overlook the exploration of the deep embedding space of the sequence. To tackle these challenges, we propose a Sparse Enhanced Network (SparseEnNet), which is a robust adversarial generation method. SparseEnNet aims to fully explore the hidden space in sequence recommendation, generating more robust enhanced items. Additionally, we adopt an adversarial generation method, allowing the model to differentiate between data augmentation categories and achieve better prediction performance for the next item in the sequence. Experiments have demonstrated that our method achieves a remarkable 4-14% improvement over existing methods when evaluated on the real-world datasets. (https://github.com/junyachen/SparseEnNet)

PDF Details DOI