AIConfPaper
← Search

Lijun Sheng

8 accepted papers

2026

LEARNING FAIR DOMAIN ADAPTATION WITH VIRTUAL LABEL DISTRIBUTION

Yuguang Zhang, NLPR & MAIS, China Electronics Standardization Insitute, Lijun Sheng, NLPR & MAIS, Jian Liang +1
ICASSP 2026poster

Unsupervised Domain Adaptation (UDA) aims to mitigate performance degradation when training and testing data are sampled from different distributions. While significant progress has been made in enhancing overall accuracy, most existing methods overlook performance disparities across categories-an i…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Cooperative Pseudo Labeling for Unsupervised Federated Classification

Kuangpu Guo, Lijun Sheng, Yongcan Yu, Jian Liang, Zilei Wang, Ran He
ICCV 2025poster

Unsupervised federated learning (UFL) aims to collaboratively train a global model across distributed clients without data sharing and label information. Previous UFL works have predominantly focused on representation learning and clustering tasks. Recently, vision language models (e.g., CLIP) have…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Protecting Model Adaptation from Trojans in the Unlabeled Data

Lijun Sheng, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
AAAI 2025technical

Model adaptation tackles the distribution shift problem with a pre-trained model instead of raw data, which has become a popular paradigm due to its great privacy protection. Existing methods always assume adapting to a clean target domain, overlooking the security risks of unlabeled samples. This p…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

Lijun Sheng, Jian Liang, Zilei Wang, Ran He
CVPR 2025poster

Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and the common practice of selecting from a limited set of open-s…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models

Lijun Sheng, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
NeurIPS 2025poster

Test-time adaptation (TTA) methods have gained significant attention for enhancing the performance of vision-language models (VLMs) such as CLIP during inference, without requiring additional labeled data. However, current TTA researches generally suffer from major limitations such as duplication of…

Cited by 0Source ↗code ↗Scholar ↗
2024

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation

Zhengbo Wang, Jian Liang, Lijun Sheng, Ran He, Zilei Wang, Tieniu Tan
ICLR 2024poster

Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods, such as prompt learning and adapter, to enhance CLIP's performance in downstream tasks. However, these methods still req…

Cited by 29Source ↗PDF ↗code ↗Scholar ↗
2024

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization

Jian Liang, Lijun Sheng, Zhengbo Wang, Ran He, Tieniu Tan
ICML 2024spotlight

The emergence of vision-language models, such as CLIP, has spurred a significant research effort towards their application for downstream supervised learning tasks. Although some previous studies have explored the unsupervised fine-tuning of CLIP, they often rely on prior knowledge in the form of cl…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2024

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay

Yu Yongcan, Lijun Sheng, Ran He, Jian Liang*
ECCV 2024poster

"Test-time adaptation (TTA) aims to address the distribution shift between the training and test data with only unlabeled data at test time. Existing TTA methods often focus on improving recognition performance specifically for test data associated with classes in the training set. However, during t…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗