Distribution Disagreement via Lorentzian Focal Representation.
- Publisher:
- Institute of Electrical and Electronics Engineers
- Publication Type:
- Journal Article
- Citation:
- IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, PP, (10), pp. 6872-6889
- Issue Date:
- 2022-06-30
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Distribution_Disagreement_via_Lorentzian_Focal_Representation.pdf | Published version | 3.5 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Error disagreement-based active learning (AL) selects the data that maximally update the error of a classification hypothesis. However, poor human supervision (e.g. few labels, improper classifier parameters) may weaken or clutter this update; moreover, the computational cost of performing a greedy search to estimate the errors using a deep neural network is intolerable. In this paper, a novel disagreement coefficient based on distribution, not error, provides a tighter bound on label complexity, which further guarantees its generalization in hyperbolic space. The focal points derived from the squared Lorentzian distance, present more effective hyperbolic representations on aspherical distribution from geometry, replacing the typical Euclidean, kernelized, and Poincar centroids. Experiments on different deep AL tasks show that, the focal representation adopted in a tree-likeliness splitting, significantly perform better than typical baselines of geometric centroids and error disagreement, and state-of-the-art neural network architectures-based AL, dramatically accelerating the learning process.
Please use this identifier to cite or link to this item: