activity
20222024
most citedOn the Strong Correlation Between Model Invariance and Generalization

5 citations · 13 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV20244 cited

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…

cs.CV20233 cited

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…

cs.LG2023

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…

cs.LG20231 cited

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…

cs.LG20225 cited

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…