Pith. sign in

REVIEW 2 cited by

SLURP: Side Learning Uncertainty for Regression Problems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.11182 v2 pith:57ZRNUHI submitted 2021-10-21 cs.CV cs.LG

classification cs.CVcs.LG
keywords regressionestimationoutputproblemsslurpuncertaintyadditioncomputer
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A post-hoc GPLVM adapter learns probabilistic embeddings from frozen CLIP and BLIP embeddings and reports state-of-the-art calibration on retrieval, VQA, and active learning benchmarks.

  2. A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation

    cs.CV 2025-01 conditional novelty 4.0 of 10

    Fine-tuning DepthAnythingV2 with a Gaussian negative log-likelihood loss yields the most reliable pixel-wise uncertainty estimates on indoor, street, and object scenes, but it fails on aerial large-depth data.

Pith tools