Generalized Multi-view Shared Subspace Learning using View Bootstrapping
Somandepalli, Krishna, Narayanan, Shrikanth
A key objective in multi-view learning is to model the information common to multiple parallel views of a class of objects/events to improve downstream learning tasks. In this context, two open research questions remain: How can we model hundreds of views per event? Can we learn robust multi-view embeddings without any knowledge of how these views are acquired? We present a neural method based on multi-view correlation to capture the information shared across a large number of views by subsampling them in a view-agnostic manner during training. To provide an upper bound on the number of views to subsample for a given embedding dimension, we analyze the error of the bootstrapped multi-view correlation objective using matrix concentration theory. Our experiments on spoken word recognition, 3D object classification and pose-invariant face recognition demonstrate the robustness of view bootstrapping to model a large number of views. Results underscore the applicability of our method for a view-agnostic learning setting.
May-12-2020
- Country:
- North America > United States > California (0.04)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Health & Medicine > Therapeutic Area > Neurology (0.93)
- Technology:
- Information Technology > Artificial Intelligence
- Vision > Face Recognition (0.89)
- Machine Learning
- Statistical Learning (1.00)
- Performance Analysis > Accuracy (0.72)
- Neural Networks > Deep Learning (0.46)
- Information Technology > Artificial Intelligence