When does Privileged information Explain Away Label Noise?
Jul 24, 2023
Speakers
Guillermo Ortiz Jimenez
Speaker · 0 followers
Mark Collier
Speaker · 0 followers
Anant Nawalgaria
Speaker · 0 followers
Alexander D'Amour
Speaker · 1 follower
Jesse Berent
Speaker · 0 followers
Rodolphe Jenatton
Speaker · 0 followers
Efi Kokiopoulou
Speaker · 0 followers
About
Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. However, the reasons for its effectiveness are not well understood. In this study, we investigate the role played by different properties of the PI in explaining away label noise. Through experiments on multiple datasets with real PI (CIFAR-N/H) and a new large-scale benchmark ImageNet-PI, we find that PI is most helpful when it allows networks to easily distinguish clean from noisy data, while enabling a learning shortcut to memorize the noisy examples. Interestingly, when PI becomes too predictive of the target label, PI methods often perform worse than their no-PI baselines. Based on these findings, we propose several enhancements to the state-of-the-art PI methods and demonstrate the potential of PI as a means of tackling label noise. Finally, we show how we can easily combine the resulting PI approaches with existing no-PI techniques designed to deal with label noise.Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. However, the reasons for its effectiveness are not well understood. In this study, we investigate the role played by different properties of the PI in explaining away label noise. Through experiments on multiple datasets with real PI (CIFAR-N/H) and a new large-scale benchmark ImageNet-PI, we find that PI is most helpful…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Automatic Data Augmentation via Invariance-Constrained Learning
Watch later
Moderately Distributional Exploration for Domain Generalization
Watch later
Rui Dai, …
MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action
Watch later
Geonho Hwang, …
Learning and using a multimodal single cell atlas
Watch later
Fabian Theis, …
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
Watch later
Yiwei Lu, …
