250 citations · 532 across the 72 of their papers we have counts for
4 papers · 2 filters
On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law
Damien Teney, Kushal Kafle, Robik Shrestha +3
Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set. OOD benchmarks are d…
Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision
Damien Teney, Ehsan Abbasnedjad, Anton van den Hengel
One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task…
Optimistic Agent: Accurate Graph-Based Value Estimation for More Successful Visual Navigation
Mahdi Kazemi Moghaddam, Qi Wu, Ehsan Abbasnejad +1
We humans can impeccably search for a target object, given its name only, even in an unseen environment. We argue that this ability is largely due to three main reasons: the incorp…
Unshuffling Data for Improved Generalization
Damien Teney, Ehsan Abbasnejad, Anton van den Hengel
Generalization beyond the training distribution is a core challenge in machine learning. The common practice of mixing and shuffling examples when training neural networks may not…