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.
2024
Inspired by AI? A Novel Generative AI System To Assist Conceptual Automotive DesignThis research explores using generative AI to streamline automotive…
2023
Language Model Crossover: Variation through Few-Shot PromptingPursuing the insight that language models naturally enable an…
2021
RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud ClassifiersThe 3D deep learning community has seen significant strides in…
2020
PointMask: Towards Interpretable and Bias-Resilient Point Cloud ProcessingDeep classifiers tend to associate a few discriminative input…
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