cs.CVJun 16, 2024

Sfumato Supervision: Learning Instance Segmentation with Noisy Labels

Authors: Moshe Kimhi, Ehud Rivlin, Chaim Baskin

Organizations: Technion · Ben-Gurion University of the Negev

Abstract

Instance segmentation requires precise object masks, yet both human annotators and promptable models can produce unreliable contours. A high prediction loss near a contour does not necessarily indicate an annotation error: valid edges can also be uncertain. Inspired by Leonardo da Vinci's sfumato, which softens transitions between a subject and its surroundings, we introduce CB-LNL (Copula-Boundary Learning with Noisy Labels). Rather than judging each contour pixel alone, CB-LNL combines foreground evidence inside the mask with background evidence outside it to guide local supervision and annotation repair. We ground this approach in an audit of paired COCO and LVIS annotations, and introduce benchmarks covering human annotations, weak-prompt SAM2 masks, and controlled corruptions in natural and driving scenes. Controlled comparisons show improved training on procedural contour noise and fewer harmful edits than direct teacher-mask replacement. Paired-seed and frozen-prediction evaluations reveal how these benefits depend on the annotation source, supporting separate assessment of category and contour reliability.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Hybrid supervised instance segmentation by learning label noise suppression

    Oct 14, 2026Linwei Chen, Ying Fu, Shaodi You +1Instance SegmentationPseudo-Labeling

  2. Boundary-by-Mask: Few-Shot Instance Segmentation with Mask-Conditioned Boundary Learning for Texture-Poor Industrial Parts

    Jun 19, 2026Yutaka Yoshinaga, Naoya Chiba, Koichi HashimotoInstance SegmentationIndustrial Inspection

  3. Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting

    Mar 17, 2026Jiyang Huang, Hongru Chen, Wei Lin +2Crowd CountingInstance Segmentation