Timezone: »

Robust Representation Learning via Perceptual Similarity Metrics
Saeid A Taghanaki · Kristy Choi · Amir Hosein Khasahmadi · Anirudh Goyal

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @ Virtual #None

A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream classification task, without overfitting to spurious input features. Extracting such task-relevant predictive information becomes particularly difficult for noisy and high-dimensional real-world data. In this work, we propose Contrastive Input Morphing (CIM), a representation learning framework that learns input-space transformations of the data to mitigate the effect of irrelevant input features on downstream performance. Our method leverages a perceptual similarity metric via a triplet loss to ensure that the transformation preserves task-relevant information. Empirically, we demonstrate the efficacy of our approach on various tasks which typically suffer from the presence of spurious correlations: classification with nuisance information, out-of-distribution generalization, and preservation of subgroup accuracies. We additionally show that CIM is complementary to other mutual information-based representation learning techniques, and demonstrate that it improves the performance of variational information bottleneck (VIB) when used in conjunction.

Author Information

Saeid A Taghanaki (Autodesk AI Lab)
Kristy Choi (Stanford University)
Amir Hosein Khasahmadi (Autodesk AI Lab)
Anirudh Goyal (Université de Montréal)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors