Model-agnostic Body Part Relevance Assessment for Pedestrian Detection

Model-agnostic explanation methods for deep learning models are flexible regarding usability and availability. However, due to the fact that they can only manipulate input to see changes in output, they suffer from weak performance when used with complex model architectures. For models with large inputs as, for instance, in object detection, sampling-based methods like KernelSHAP are inefficient due to many computation-heavy forward passes through the model. In this work, we present a framework for using sampling-based explanation models in a computer vision context by body part relevance assessment for pedestrian detection. Furthermore, we introduce a novel sampling-based method similar to KernelSHAP that shows more robustness for lower sampling sizes and, thus, is more efficient for explainability analyses on large-scale datasets.

  • Published in:
    arXiv
  • Type:
    Article
  • Authors:
    Günder, Maurice; Banerjee, Sneha; Sifa, Rafet; Bauckhage, Christian
  • Year:
    2023

Citation information

Günder, Maurice; Banerjee, Sneha; Sifa, Rafet; Bauckhage, Christian: Model-agnostic Body Part Relevance Assessment for Pedestrian Detection, arXiv, 2023, https://arxiv.org/abs/2311.15679, Guender.etal.2023a,

Associated Lamarr Researchers

Prof. Dr. Rafet Sifa

Prof. Dr. Rafet Sifa

Principal Investigator Hybrid ML to the profile
lamarr institute person Bauckhage Christian - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Prof. Dr. Christian Bauckhage

Director to the profile