Pith. sign in

REVIEW 1 cited by

MEAL: Manifold Embedding-based Active Learning

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 2106.11858 v3 pith:ECMJ5JBM submitted 2021-06-22 cs.CV cs.LG

classification cs.CVcs.LG
keywords learningactivemethodautonomousdatadrivingimagemanifold
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Image segmentation is a common and challenging task in autonomous driving. Availability of sufficient pixel-level annotations for the training data is a hurdle. Active learning helps learning from small amounts of data by suggesting the most promising samples for labeling. In this work, we propose a new pool-based method for active learning, which proposes promising patches extracted from full image, in each acquisition step. The problem is framed in an exploration-exploitation framework by combining an embedding based on Uniform Manifold Approximation to model representativeness with entropy as uncertainty measure to model informativeness. We applied our proposed method to the autonomous driving datasets CamVid and Cityscapes and performed a quantitative comparison with state-of-the-art baselines. We find that our active learning method achieves better performance compared to previous methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation

    cs.CV 2024-12 conditional novelty 5.0 of 10

    OREAL improves patch-based active learning for semantic segmentation by scoring superpixels with their maximum pixel uncertainty and using one-vs-rest entropy to balance classes.

Pith tools