Damien Teney

Affiliations

Idiap Research InstituteUniversity of Adelaide

papers

1,087

total citations

papers (20)

Image Retrieval on Real-Life Images With Pre-Trained Vision-and-Language Models

ICCV 2021arXiv

305

citations

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

NEURIPS 2020arXiv

155

citations

Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision

ECCV 2020arXiv

125

citations

Active Learning by Feature Mixing

CVPR 2022arXiv

115

citations

Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization

CVPR 2022arXiv

103

citations

Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering

ICCV 2021arXiv

citations

ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets

NEURIPS 2023arXiv

citations

Neural Redshift: Random Networks are not Random Functions

CVPR 2024arXiv

citations

SelecMix: Debiased Learning by Contradicting-pair Sampling

NEURIPS 2022arXiv

citations

Predicting Is Not Understanding: Recognizing and Addressing Underspecification in Machine Learning

ECCV 2022arXiv

citations

Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup

ICML 2024arXiv

citations

Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild

CVPR 2025arXiv

citations

Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks

AAAI 2025arXiv

citations

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?

ICML 2025arXiv

citations

AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition

NEURIPS 2025arXiv

citations

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

ICLR 2025arXiv

citations

Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection

NEURIPS 2025arXiv

citations

Damien Teney

Affiliations

papers (20)

Image Retrieval on Real-Life Images With Pre-Trained Vision-and-Language Models

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision

Active Learning by Feature Mixing

Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization

Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering

ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets

Neural Redshift: Random Networks are not Random Functions

SelecMix: Debiased Learning by Contradicting-pair Sampling

Predicting Is Not Understanding: Recognizing and Addressing Underspecification in Machine Learning

Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup

Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild

Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?

AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

Unshuffling Data for Improved Generalization in Visual Question Answering

Counterfactual Vision-and-Language Navigation: Unravelling the Unseen

Counterfactual Vision and Language Learning

Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection

papers (20)

Image Retrieval on Real-Life Images With Pre-Trained Vision-and-Language Models

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision

Active Learning by Feature Mixing

Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization

Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering

ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets

Neural Redshift: Random Networks are not Random Functions

SelecMix: Debiased Learning by Contradicting-pair Sampling

Predicting Is Not Understanding: Recognizing and Addressing Underspecification in Machine Learning

Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup

Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild

Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?

AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

Unshuffling Data for Improved Generalization in Visual Question Answering

Counterfactual Vision-and-Language Navigation: Unravelling the Unseen

Counterfactual Vision and Language Learning

Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection