A Mathematical Analysis of Learning Loss for Active Learning in Regression

by   Megh Shukla, et al.

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.


page 2

page 6


Learning Loss for Active Learning

The performance of deep neural networks improves with more annotated dat...

EGL++: Extending Expected Gradient Length to Active Learning for Human Pose Estimation

State of the art human pose estimation models continue to rely on large ...

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

Advances in computing have enabled widespread access to pose estimation,...

FasterPose: A Faster Simple Baseline for Human Pose Estimation

The performance of human pose estimation depends on the spatial accuracy...

Failure-averse Active Learning for Physics-constrained Systems

Active learning is a subfield of machine learning that is devised for de...

Nuclear Discrepancy for Active Learning

Active learning algorithms propose which unlabeled objects should be que...

HiddenGems: Efficient safety boundary detection with active learning

Evaluating safety performance in a resource-efficient way is crucial for...

Please sign up or login with your details

Forgot password? Click here to reset