Kuo Shi

Kuo Shi

Auto-generated profile, based on publicly available information

Kuo Shi

Australian Artificial Intelligence Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 April 2024 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
KSKuo Shi
Kuo Shi
JLJie Lu
Jie Lu
ZFZhen Fang
Zhen Fang
GZGuangquan Zhang
Guangquan Zhang
Unsupervised Domain Adaptation (UDA) addresses the challenge of distribution shift between a labeled source domain and an unlabeled target domain by utilizing knowledge from the source. Traditional UDA methods mainly focus on single-modal scenarios, either vision or language, thus not fully exploring the advantages of multi-modal representations. Vision-Language models utilize multi-modal information, applying prompt learning techniques for addressing target domain tasks. Motivated by the recent advancements in pre-trained Vision-Language models, this paper expands the UDA framework to incorporate multi-modal approaches using fuzzy techniques. The adoption of fuzzy techniques, preferred over conventional domain adaptation methods, is based on two key aspects: the nature of prompt learning is intrinsically linked to fuzzy logic, and the superior capability of fuzzy techniques in processing soft information and effectively utilizing inherent relationships both within and across domains. To this end, we propose UDA enhanced by Fuzz y Prompt Le arning (FUZZLE), a simple and effective method for aligning the source and target domains via domain-specific prompt learning. Specifically, we introduce a novel technique to enhance prompt learning in the target domain. This method integrates fuzzy C-means clustering and a novel instance-level fuzzy vector into the prompt learning loss function, minimizing the distance between prompt cluster centers and instance prompts, thereby enhancing the prompt learning process. In addition, we propose a Kullback-Leibler (KL) divergence-based loss function with a fuzzification factor. This function is designed to minimize the distribution discrepancy in the classification of similar cross-domain data, aligning domain-specific prompts during the training process. We contribute an in-depth analysis to understand the effectiveness of Extensive experiments demonstrate that our method achieves superior performance on standard UDA benchmarks.


11 February 2026 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
KSKuo Shi
Kuo Shi
JLJie Lu
Jie Lu
ZFZhen Fang
Zhen Fang
GZGuangquan Zhang
Guangquan Zhang
Unsupervised domain adaptation (UDA) aims to improve a model’s performance on an unlabeled target domain by leveraging labeled data from a source domain. Traditional UDA methods often overlook the rich textual information inherent in class labels, limiting their effectiveness. Recent advances in visual language models (VLMs), especially the contrastive language–image pretraining (CLIP) model, provide a promising multimodal foundation by integrating both image and text representations. However, most CLIP-based UDA approaches rely on pseudo-labels generated in a zero-shot manner by the pretrained CLIP model, which may become suboptimal as training progresses. To address this limitation, we propose a pseudo-label refinement (PuRe) framework that begins training with zero-shot CLIP pseudo-labels and then transitions to self-training, where we iteratively refine the model’s own predictions as pseudo-labels. In this iterative process, we introduce label consistency learning to stabilize predictions under strong data augmentations, increasing robustness, and an information maximization (IM) loss to encourage high-confidence predictions while preserving prediction diversity. Together, these components progressively enhance pseudo-label reliability, leading to improved adaptation in the target domain. Furthermore, we propose a novel prompt learning (PL) method that fine-tunes only a minimal set of parameters, specifically a single context token and class embeddings. Extensive experiments demonstrate that PuRe surpasses existing UDA methods on multiple benchmarks.

31 January 2025
Verified
Preprint
Open access
PDF file
KSKuo Shi
Kuo Shi
Comments: 1. While the paper discusses misalignment, it does not review existing evaluation metrics for measuring alignment and misalignment. 2. The paper does not discuss how alignment challenges scale with model size. For instance, do larger LVLMs...