Logo image
Surrogate Model-based Explainability Method for 3D Object Tracking
Journal article   Open access   Peer reviewed

Surrogate Model-based Explainability Method for 3D Object Tracking

Riran Cheng, Xupeng Wang, Ferdous Sohel, Yu Peng and Hang Lei
IEEE transactions on multimedia, Early Access
2026
pdf
Explainability Method for 3D Object Tracking3.44 MBDownloadView
Open Access

Abstract

3D object tracking Cams Clouds Computer aided manufacturing Computers Conferences explainability method local explanation Matrices Modeling Object tracking superpoint surrogate model Tracking Training
3D object tracking is a popular research topic in computer vision. However, it remains a challenging task to improve the trustworthiness of deep 3D trackers, due to the complex network structures of these black-box models. In this paper, an explainability method is designed to generate local explanations for 3D object tracking, which trains an interpretable surrogate model to reveal the contributions of superpoints in the search area to the decision-making of a 3D tracker. Specifically, local points within the search area with comparable geometric features are aggregated into superpoints, which serve as the basis for the explanation, and non-negative matrix factorization is employed to uncover latent features of the search area. In contrast to the commonly used voxels, the representation of superpoints captures rich semantic information of the search area, and facilitates an intuitive understanding of the explanations. To train the surrogate model, an adaptive downsampling strategy is proposed to generate the sample set by removing superpoints, with the latent contributions of superpoints to predictions considered to improve explanation efficacy. Additionally, each sample is weighted during training to better approximate the decision of a 3D tracker. Experiments have demonstrated that the proposed explainability approach can effectively provide explanations to multiple deep tracking models on three large-scale datasets.

Details

Metrics

1 File views/ downloads
4 Record Views
Logo image