CVFeb 27, 2021

Successive Subspace Learning: An Overview

arXiv:2103.00121v115 citations
AI Analysis

This is an incremental overview paper summarizing an existing method for researchers in unsupervised learning.

The paper provides an overview of Successive Subspace Learning (SSL), a lightweight unsupervised feature learning method that leverages statistical properties of data units, noting its promising results on small datasets.

Successive Subspace Learning (SSL) offers a light-weight unsupervised feature learning method based on inherent statistical properties of data units (e.g. image pixels and points in point cloud sets). It has shown promising results, especially on small datasets. In this paper, we intuitively explain this method, provide an overview of its development, and point out some open questions and challenges for future research.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes