Publication
Robust Representation Learning via Perceptual Similarity Metrics
AbstractA fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features. Extracting such task-relevant predictive information is particularly difficult for real-world datasets. 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 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 together.
Download publicationRelated Resources
See what’s new.
01/01/2021
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
We explore how the lens of fictional superpowers can help characterize…
01/01/2017
Experimental Evaluation of Sketching on Surfaces in VR
Sketching in immersive 3D virtual reality (VR) environments has great…
01/01/2021
Collective Transport of Unconstrained Objects via Implicit Coordination and Adaptive Compliance
We present a decentralized control algorithm for robots to aid in…
01/01/2019
Command Usage Arc Diagrams | Autodesk Research
Exploring and analyzing a database of over 60 million commands issued…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us