SLURP: Side Learning Uncertainty for Regression Problems
This addresses the need for reliable uncertainty quantification in regression tasks for computer vision applications, though it appears incremental as it builds on existing uncertainty estimation methods.
The authors tackled uncertainty estimation in regression problems by proposing SLURP, a side learner that uses outputs and intermediate representations from the main model, and demonstrated its effectiveness on monocular depth and optical flow estimation with low computational cost.
It has become critical for deep learning algorithms to quantify their output uncertainties to satisfy reliability constraints and provide accurate results. Uncertainty estimation for regression has received less attention than classification due to the more straightforward standardized output of the latter class of tasks and their high importance. However, regression problems are encountered in a wide range of applications in computer vision. We propose SLURP, a generic approach for regression uncertainty estimation via a side learner that exploits the output and the intermediate representations generated by the main task model. We test SLURP on two critical regression tasks in computer vision: monocular depth and optical flow estimation. In addition, we conduct exhaustive benchmarks comprising transfer to different datasets and the addition of aleatoric noise. The results show that our proposal is generic and readily applicable to various regression problems and has a low computational cost with respect to existing solutions.