Publication | International Conference on Machine Learning 2021
Robust Representation Learning via Perceptual Similarity Metrics
This paper introduces a general framework for learning representations from images/objects that are invariant to bias in data for downstream classification tasks.
Download publicationAbstract
Robust Representation Learning via Perceptual Similarity Metrics
Saeid Asgari Taghanaki, Kristy Choi, Amir Khasahmadi, Anirudh Goyal
International Conference on Machine Learning 2021
A 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.
Related Resources
See what’s new.
2025
Towards Interactive AI-assisted Material Selection for Sustainable Building DesignAn AI-assisted workflow uses graph-based representations of wall…
2024
HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in Computer-Aided DesignThis work presents a new Machine Learning architecture to support…
2022
CLIP-Forge: Towards Zero-Shot Text-to-Shape GenerationGenerating shapes using natural language can enable new ways of…
2021
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design SequencesParametric computer-aided design (CAD) is a standard paradigm used to…
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