168 citations · 281 across the 10 of their papers we have counts for
11 papers
SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning
Qi Qian, Yuanhong Xu, Juhua Hu
Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear p…
Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP
Qi Qian, Yuanhong Xu, Juhua Hu
Vision-language pre-training methods, e.g., CLIP, demonstrate an impressive zero-shot performance on visual categorizations with the class proxy from the text embedding of the clas…
mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
Qinghao Ye, Haiyang Xu, Guohai Xu +15
Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-mo…
Improved Visual Fine-tuning with Natural Language Supervision
Junyang Wang, Yuanhong Xu, Juhua Hu +3
Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks wit…
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
Haiyang Xu, Qinghao Ye, Ming Yan +12
Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for…
An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation
Ziquan Liu, Yi Xu, Yuanhong Xu +5
The performance of machine learning models under distribution shift has been the focus of the community in recent years. Most of current methods have been proposed to improve the r…
Improved Fine-Tuning by Better Leveraging Pre-Training Data
Ziquan Liu, Yi Xu, Yuanhong Xu +5
As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studie…
Unsupervised Visual Representation Learning by Online Constrained K-Means
Qi Qian, Yuanhong Xu, Juhua Hu +2
Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to as…
Towards Understanding Label Smoothing
Yi Xu, Yuanhong Xu, Qi Qian +2
Label smoothing regularization (LSR) has a great success in training deep neural networks by stochastic algorithms such as stochastic gradient descent and its variants. However, th…
Weakly Supervised Representation Learning with Coarse Labels
Yuanhong Xu, Qi Qian, Hao Li +2
With the development of computational power and techniques for data collection, deep learning demonstrates a superior performance over most existing algorithms on visual benchmark…
Combining SLAM with muti-spectral photometric stereo for real-time dense 3D reconstruction
Yuanhong Xu, Pei Dong, Junyu Dong +1
Obtaining dense 3D reconstrution with low computational cost is one of the important goals in the field of SLAM. In this paper we propose a dense 3D reconstruction framework from m…