Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection

no code implementations • 29 May 2024 • Yushu Li, Yongyi Su, Xulei Yang, Kui Jia, Xun Xu

In this work, we are motivated by a pitfall of TTA, i. e. sensitive to hyper-parameters, and propose to approach HILTTA by synergizing active learning and model selection.

Dynamic Shuffle: An Efficient Channel Mixture Method

no code implementations • 4 Oct 2023 • Kaijun Gong, Zhuowen Yin, Yushu Li, Kailing Guo, Xiangmin Xu

To reduce the data-dependent redundancy, we devise a dynamic shuffle module to generate data-dependent permutation matrices for shuffling.

Binarization Image Classification

On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion

1 code implementation • ICCV 2023 • Yushu Li, Xun Xu, Yongyi Su, Kui Jia

Existing approaches often focus on improving test-time training performance under well-curated target domain data.

A Bayesian Lasso based Sparse Learning Model

no code implementations • 20 Aug 2019 • Ingvild M. Helgøy, Yushu Li

This paper develops a new sparse learning model, named the Bayesian Lasso Sparse (BLS) model, that takes the hierarchical model formulation of the Bayesian Lasso.

Compressive Sensing regression +1