Self-Supervised Learning from Semantically Imprecise Data

TL;DR

This paper introduces an improved self-supervised learning method that enhances hierarchical classifiers trained on imprecise labels, enabling more accurate and efficient predictions with weaker supervision.

Contribution

It extends CHILLAX by incorporating a self-supervised scheme with constrained semantic extrapolation, allowing learning from root-level labels and generating pseudo-labels during training.

Findings

Achieves a 0.84 to 1.19 percentage point accuracy improvement over CHILLAX.

Operates as a drop-in replacement without increasing training time.

Effectively learns from weaker supervision signals.

Abstract

Learning from imprecise labels such as "animal" or "bird", but making precise predictions like "snow bunting" at inference time is an important capability for any classifier when expertly labeled training data is scarce. Contributions by volunteers or results of web crawling lack precision in this manner, but are still valuable. And crucially, these weakly labeled examples are available in larger quantities for lower cost than high-quality bespoke training data. CHILLAX, a recently proposed method to tackle this task, leverages a hierarchical classifier to learn from imprecise labels. However, it has two major limitations. First, it does not learn from examples labeled as the root of the hierarchy, e.g., "object". Second, an extrapolation of annotations to precise labels is only performed at test time, where confident extrapolations could be already used as training data. In this work, we extend CHILLAX with a self-supervised scheme using constrained semantic extrapolation to generate pseudo-labels. This addresses the second concern, which in turn solves the first problem, enabling an even weaker supervision requirement than CHILLAX. We evaluate our approach empirically, showing that our method allows for a consistent accuracy improvement of 0.84 to 1.19 percent points over CHILLAX and is suitable as a drop-in replacement without any negative consequences such as longer training times.