# Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent Driving

arXiv: https://arxiv.org/abs/2409.00839 · HTML: https://mlsanity.com/paper/2409.00839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 41 references that are in the map.
- First posted on arXiv 1 Sep 2024.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback](https://mlsanity.com/paper/1911.11174/) (2019)
- [Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey](https://mlsanity.com/paper/1911.12116/) (2019)
- [Multi-modal Graph Learning for Disease Prediction](https://mlsanity.com/paper/2203.05880/) (2022)
- [Autonomous Navigation in Complex Environments with Deep Multimodal Fusion Network](https://mlsanity.com/paper/2007.15945/) (2020)
- [RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving](https://mlsanity.com/paper/2012.15072/) (2020)
- [A novel multimodal fusion network based on a joint coding model for lane line segmentation](https://mlsanity.com/paper/2103.11114/) (2021)
- [Autonomous Vehicles for Smart and Sustainable Cities: An In-Depth Exploration of Privacy and Cybersecurity Implications](https://mlsanity.com/paper/1804.10367/) (2018)

## Abstract (arXiv)

With the increasing complexity of the traffic environment, the significance of safety perception in intelligent driving is intensifying. Traditional methods in the field of intelligent driving perception rely on deep learning, which suffers from limited interpretability, often described as a "black box." This paper introduces a novel type of loss function, termed "Entropy Loss," along with an innovative training strategy. Entropy Loss is formulated based on the functionality of feature compression networks within the perception model. Drawing inspiration from communication systems, the information transmission process in a feature compression network is expected to demonstrate steady changes in information volume and a continuous decrease in information entropy. By modeling network layer outputs as continuous random variables, we construct a probabilistic model that quantifies changes in information volume. Entropy Loss is then derived based on these expectations, guiding the update of network parameters to enhance network interpretability. Our experiments indicate that the Entropy Loss training strategy accelerates the training process. Utilizing the same 60 training epochs, the accuracy of 3D object detection models using Entropy Loss on the KITTI test set improved by up to 4.47% compared to models without Entropy Loss, underscoring the method's efficacy. The implementation code is available at https://github.com/yhbcode000/Eloss-Interpretability.