Probabilistic Object Classification using CNN ML-MAP layers

TL;DR

This paper introduces a probabilistic CNN classification method using ML and MAP layers in the Logit space, improving overconfidence issues of SoftMax for autonomous driving data.

Contribution

It presents a novel probabilistic layer design for CNNs enabling Bayesian inference, enhancing confidence calibration in object classification tasks.

Findings

Improved calibration of prediction confidence.

Better performance on KITTI dataset.

Effective in both RGB and LiDAR modalities.

Abstract

Deep networks are currently the state-of-the-art for sensory perception in autonomous driving and robotics. However, deep models often generate overconfident predictions precluding proper probabilistic interpretation which we argue is due to the nature of the SoftMax layer. To reduce the overconfidence without compromising the classification performance, we introduce a CNN probabilistic approach based on distributions calculated in the network's Logit layer. The approach enables Bayesian inference by means of ML and MAP layers. Experiments with calibrated and the proposed prediction layers are carried out on object classification using data from the KITTI database. Results are reported for camera ($RGB$) and LiDAR (range-view) modalities, where the new approach shows promising performance compared to SoftMax.