CISPA
Browse

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

Download (9.67 MB)
conference contribution
posted on 2024-07-17, 11:27 authored by Alaa Anani, Tobias LorenzTobias Lorenz, Bernt Schiele, Mario FritzMario Fritz
Common certification methods operate on a flat pre-defined set of fine-grained classes. In this paper, however, we propose a novel, more general, and practical setting, namely adaptive hierarchical certification for image semantic segmentation. In this setting, the certification can be within a multi-level hierarchical label space composed of fine to coarse levels. Unlike classic methods where the certification would abstain for unstable components, our approach adaptively relaxes the certification to a coarser level within the hierarchy. This relaxation lowers the abstain rate whilst providing more certified semantically meaningful information. We mathematically formulate the problem setup and introduce, for the first time, an adaptive hierarchical certification algorithm for image semantic segmentation, that certifies image pixels within a hierarchy and prove the correctness of its guarantees. Since certified accuracy does not take the loss of information into account when traversing into a coarser hierarchy level, we introduce a novel evaluation paradigm for adaptive hierarchical certification, namely the certified information gain metric, which is proportional to the class granularity level. Our evaluation experiments on real-world challenging datasets such as Cityscapes and ACDC demonstrate that our adaptive algorithm achieves a higher certified information gain and a lower abstain rate compared to the current state-of-the-art certification method, as well as other non-adaptive versions of it.

History

Primary Research Area

  • Reliable Security Guarantees

Secondary Research Area

  • Trustworthy Information Processing

Name of Conference

International Conference on Machine Learning (ICML)

Journal

Forty-first International Conference on Machine Learning

Open Access Type

  • Gold

BibTeX

@conference{Anani:Lorenz:Schiele:Fritz:2024, title = "Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing", author = "Anani, Alaa" AND "Lorenz, Tobias" AND "Schiele, Bernt" AND "Fritz, Mario", year = 2024, month = 7, journal = "Forty-first International Conference on Machine Learning" }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC