6 citations · 16 across the 19 of their papers we have counts for
21 papers
Refining Open-Vocabulary Semantic Segmentation via Regional Semantics and Visual Prototypes
Aijing Yu, Zhengbo Wang, Lijun Sheng +2
Contrastive Language-Image Pre-training (CLIP) has shown superior performance in the image-level open-vocabulary classification task, benefiting from its powerful alignment of visu…
Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation
Shuo Lu, Jianjie Cheng, Yinuo Xu +16
Multimodal large language models (MLLMs) have achieved strong performance on perception-oriented tasks, yet their ability to perform mathematical spatial reasoning, defined as the…
Learning Fair Domain Adaptation with Virtual Label Distribution
Yuguang Zhang, Lijun Sheng, Jian Liang +1
Unsupervised Domain Adaptation (UDA) aims to mitigate performance degradation when training and testing data are sampled from different distributions. While significant progress ha…
Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning
Yongcan Yu, Lingxiao He, Shuo Lu +10
Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away fro…
Cooperative Pseudo Labeling for Unsupervised Federated Classification
Kuangpu Guo, Lijun Sheng, Yongcan Yu +3
Unsupervised Federated Learning (UFL) aims to collaboratively train a global model across distributed clients without sharing data or accessing label information. Previous UFL work…
Adapting Vision-Language Models Without Labels: A Comprehensive Survey
Hao Dong, Lijun Sheng, Jian Liang +3
Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when direct…
The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
Lijun Sheng, Jian Liang, Ran He +2
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…
R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
Lijun Sheng, Jian Liang, Zilei Wang +1
Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstre…
Towards Compatible Fine-tuning for Vision-Language Model Updates
Zhengbo Wang, Jian Liang, Lijun Sheng +3
So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules. However, exis…
Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain Adaptation
Jian Liang, Lijun Sheng, Hongmin Liu +1
Unsupervised domain adaptation aims to transfer knowledge from a related, label-rich source domain to an unlabeled target domain, thereby circumventing the high costs associated wi…
Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances
Shuo Lu, Yingsheng Wang, Lijun Sheng +3
Out-of-distribution (OOD) detection aims to detect test samples outside the training category space, which is an essential component in building reliable machine learning systems.…
STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
Yongcan Yu, Lijun Sheng, Ran He +1
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 impr…
Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection
Yuting Xu, Jian Liang, Lijun Sheng +1
The deepfake threats to society and cybersecurity have provoked significant public apprehension, driving intensified efforts within the realm of deepfake video detection. Current v…
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Zhengbo Wang, Jian Liang, Lijun Sheng +3
Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods,…
Protecting Model Adaptation from Trojans in the Unlabeled Data
Lijun Sheng, Jian Liang, Ran He +2
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. Exist…
Self-training solutions for the ICCV 2023 GeoNet Challenge
Lijun Sheng, Zhengbo Wang, Jian Liang
GeoNet is a recently proposed domain adaptation benchmark consisting of three challenges (i.e., GeoUniDA, GeoImNet, and GeoPlaces). Each challenge contains images collected from th…
Unleashing the power of Neural Collapse for Transferability Estimation
Yuhe Ding, Bo Jiang, Lijun Sheng +2
Transferability estimation aims to provide heuristics for quantifying how suitable a pre-trained model is for a specific downstream task, without fine-tuning them all. Prior studie…
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
Jian Liang, Lijun Sheng, Zhengbo Wang +2
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 p…
Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
Yongcan Yu, Lijun Sheng, Ran He +1
Test-time adaptation (TTA) is a technique aimed at enhancing the generalization performance of models by leveraging unlabeled samples solely during prediction. Given the need for r…
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
Lijun Sheng, Jian Liang, Ran He +2
Model adaptation aims at solving the domain transfer problem under the constraint of only accessing the pretrained source models. With the increasing considerations of data privacy…
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
Yuhe Ding, Lijun Sheng, Jian Liang +2
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, s…