Revisiting Modality Imbalance In Multimodal Pedestrian Detection
Abstract
Multimodal learning, particularly for pedestrian detection, has recently received emphasis due to its capability to function equally well in several critical autonomous driving scenarios such as low-light, night-time, and adverse weather conditions. However, in most cases, the training distribution largely emphasizes the contribution of one specific input that makes the network biased towards one modality. Hence, the generalization of such models becomes a significant problem where the non-dominant input modality during training could be contributing more to the course of inference. Here, we introduce a novel training setup with regularizer in the multimodal architecture to resolve the problem of this disparity between the modalities. Specifically, our regularizer term helps to make the feature fusion method more robust by considering both the feature extractors equivalently important during the training to extract the multimodal distribution which is referred to as removing the imbalance problem. Furthermore, our decoupling concept of output stream helps the detection task by sharing the spatial sensitive information mutually. Extensive experiments of the proposed method on KAIST and UTokyo datasets shows improvement of the respective state-of-the-art performance.
Cite
@article{arxiv.2302.12589,
title = {Revisiting Modality Imbalance In Multimodal Pedestrian Detection},
author = {Arindam Das and Sudip Das and Ganesh Sistu and Jonathan Horgan and Ujjwal Bhattacharya and Edward Jones and Martin Glavin and Ciarán Eising},
journal= {arXiv preprint arXiv:2302.12589},
year = {2023}
}
Comments
5 pages, 3 figure, 4 tables