5 citations · 13 across the 5 of their papers we have counts for
5 papers
A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
Weijie Tu, Weijian Deng, Tom Gedeon
Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable generalization capabilities across multiple challenging distribution shifts. However, there is st…
A Bag-of-Prototypes Representation for Dataset-Level Applications
Weijie Tu, Weijian Deng, Tom Gedeon +1
This work investigates dataset vectorization for two dataset-level tasks: assessing training set suitability and test set difficulty. The former measures how suitable a training se…
Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift
Yuli Zou, Weijian Deng, Liang Zheng
Model calibration usually requires optimizing some parameters (e.g., temperature) w.r.t an objective function (e.g., negative log-likelihood). In this paper, we report a plain, imp…
Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation
Weijian Deng, Yumin Suh, Stephen Gould +1
This work aims to assess how well a model performs under distribution shifts without using labels. While recent methods study prediction confidence, this work reports prediction di…
On the Strong Correlation Between Model Invariance and Generalization
Weijian Deng, Stephen Gould, Liang Zheng
Generalization and invariance are two essential properties of any machine learning model. Generalization captures a model's ability to classify unseen data while invariance measure…