G2L: A Geometric Approach for Generating Pseudo-labels that Improve Transfer Learning
Transfer learning is a deep-learning technique that ameliorates the problem of learning when human-annotated labels are expensive and limited. In place of such labels, it uses instead the previously trained weights from a well-chosen source model as the initial weights for the training of a base mod...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Transfer learning is a deep-learning technique that ameliorates the problem
of learning when human-annotated labels are expensive and limited. In place of
such labels, it uses instead the previously trained weights from a well-chosen
source model as the initial weights for the training of a base model for a new
target dataset. We demonstrate a novel but general technique for automatically
creating such source models. We generate pseudo-labels according to an
efficient and extensible algorithm that is based on a classical result from the
geometry of high dimensions, the Cayley-Menger determinant. This G2L
(``geometry to label'') method incrementally builds up pseudo-labels using a
greedy computation of hypervolume content. We demonstrate that the method is
tunable with respect to expected accuracy, which can be forecast by an
information-theoretic measure of dataset similarity (divergence) between source
and target. The results of 280 experiments show that this mechanical technique
generates base models that have similar or better transferability compared to a
baseline of models trained on extensively human-annotated ImageNet1K labels,
yielding an overall error decrease of 0.43\%, and an error decrease in 4 out of
5 divergent datasets tested. |
---|---|
DOI: | 10.48550/arxiv.2207.03554 |