1 citations · 1 across the 7 of their papers we have counts for
7 papers
Neutral-Reference Prompting for Vision-Language Models
Senmao Tian, Xiang Wei, Shunli Zhang
Efficient transfer learning of vision-language models (VLMs) commonly suffers from a Base-New Trade-off (BNT): improving performance on unseen (new) classes often degrades accuracy…
Sampling Control for Imbalanced Calibration in Semi-Supervised Learning
Senmao Tian, Xiang Wei, Shunli Zhang
Class imbalance remains a critical challenge in semi-supervised learning (SSL), especially when distributional mismatches between labeled and unlabeled data lead to biased classifi…
GaitAdapt: Continual Learning for Evolving Gait Recognition
Jingjie Wang, Shunli Zhang, Xiang Wei +1
Current gait recognition methodologies generally necessitate retraining when encountering new datasets. Nevertheless, retrained models frequently encounter difficulties in preservi…
Accurate Quantization for Gait Representation Learning
S. Tian, H. Gao, G. Hong +4
Existing deep learning methods have made significant progress in gait representation learning. Quantization can facilitate the application of gait models as a model-agnostic genera…
Adaptive quantization with mixed-precision based on low-cost proxy
Junzhe Chen, Qiao Yang, Senmao Tian +1
It is critical to deploy complicated neural network models on hardware with limited resources. This paper proposes a novel model quantization method, named the Low-Cost Proxy-Based…
A Comprehensive Comparison of Projections in Omnidirectional Super-Resolution
Huicheng Pi, Senmao Tian, Ming Lu +3
Super-Resolution (SR) has gained increasing research attention over the past few years. With the development of Deep Neural Networks (DNNs), many super-resolution methods based on…
CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input
Senmao Tian, Ming Lu, Jiaming Liu +3
With the development of high-definition display devices, the practical scenario of Super-Resolution (SR) usually needs to super-resolve large input like 2K to higher resolution (4K…