A Mathematical Analysis of Learning Loss for Active Learning in Regression
This work addresses the need for theoretical grounding in active learning methods for industrial applications where model reliability is critical, though it is incremental as it builds on an existing technique.
The paper tackles the problem of providing a theoretical foundation for the empirically motivated Learning Loss active learning method in regression, proposing a modified version called LearningLoss++ that uses gradient analysis and a multi-scale convolutional architecture. The result shows that LearningLoss++ outperforms the original in identifying poor performance scenarios, leading to more reliable model refinement in human pose estimation on MPII and LSP datasets.
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.