A Mathematical Analysis of Learning Loss for Active Learning in Regression

TL;DR

This paper provides a theoretical foundation for the Learning Loss active learning method in regression, introduces an improved version called LearningLoss++, and demonstrates its effectiveness in human pose estimation tasks.

Contribution

It develops a rigorous analysis of Learning Loss, proposes LearningLoss++ with a convolutional architecture, and validates its improved performance in regression tasks.

Findings

LearningLoss++ better identifies failure scenarios in regression.

Gradient analysis reveals key differences between Learning Loss and LearningLoss++.

LearningLoss++ achieves more reliable model refinement in human pose estimation.

Abstract

Active learning continues to remain significant in the industry since it is data efficient. Not only is it cost effective on a constrained budget, continuous refinement of the model allows for early detection and resolution of failure scenarios during the model development stage. Identifying and fixing failures with the model is crucial as industrial applications demand that the underlying model performs accurately in all foreseeable use cases. One popular state-of-the-art technique that specializes in continuously refining the model via failure identification is Learning Loss. Although simple and elegant, this approach is empirically motivated. Our paper develops a foundation for Learning Loss which enables us to propose a novel modification we call LearningLoss++. We show that gradients are crucial in interpreting how Learning Loss works, with rigorous analysis and comparison of the gradients between Learning Loss and LearningLoss++. We also propose a convolutional architecture that combines features at different scales to predict the loss. We validate LearningLoss++ for regression on the task of human pose estimation (using MPII and LSP datasets), as done in Learning Loss. We show that LearningLoss++ outperforms in identifying scenarios where the model is likely to perform poorly, which on model refinement translates into reliable performance in the open world.