Probabilistic Object Classification using CNN ML-MAP layers
This addresses the issue of probabilistic interpretation in deep learning for autonomous driving, though it appears incremental as it modifies existing layers rather than introducing a new paradigm.
The paper tackled the problem of overconfident predictions in deep networks for object classification in autonomous driving by introducing a CNN probabilistic approach using ML and MAP layers, which showed promising performance compared to SoftMax on KITTI data for camera and LiDAR modalities.
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.