Probabilistic Object Classification using CNN ML-MAP layers
- URL: http://arxiv.org/abs/2005.14565v2
- Date: Mon, 24 Aug 2020 11:37:53 GMT
- Title: Probabilistic Object Classification using CNN ML-MAP layers
- Authors: G. Melotti, C. Premebida, J.J. Bird, D.R. Faria, N. Gon\c{c}alves
- Abstract summary: We introduce a CNN probabilistic approach based on distributions calculated in the network's Logit layer.
The new approach shows promising performance compared to SoftMax.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- ConvBKI: Real-Time Probabilistic Semantic Mapping Network with Quantifiable Uncertainty [7.537718151195062]
We develop a modular neural network for real-time colorblack(> 10 Hz) semantic mapping in uncertain environments.
Our approach combines the reliability of classical probabilistic algorithms with the performance and efficiency of modern neural networks.
arXiv Detail & Related papers (2023-10-24T17:30:26Z) - An Explainable Model-Agnostic Algorithm for CNN-based Biometrics
Verification [55.28171619580959]
This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting.
arXiv Detail & Related papers (2023-07-25T11:51:14Z) - Variational Classification [51.2541371924591]
We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders.
Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency.
We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
arXiv Detail & Related papers (2023-05-17T17:47:19Z) - Reducing Overconfidence Predictions for Autonomous Driving Perception [3.1428836133120543]
We show that Maximum Likelihood (ML) and Maximum a-Posteriori (MAP) functions are more suitable for probabilistic interpretations than SoftMax and Sigmoid-based predictions for object recognition.
ML and MAP functions can be implemented in existing trained networks, that is, the approach benefits from the output of the Logit layer of pre-trained networks.
arXiv Detail & Related papers (2022-02-16T01:59:55Z) - NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural
Networks [151.03112356092575]
We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution.
We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
arXiv Detail & Related papers (2022-02-07T12:30:45Z) - A deep learning based surrogate model for stochastic simulators [0.0]
We propose a deep learning-based surrogate model for simulators.
We utilize conditional maximum mean discrepancy (CMMD) as the loss-function.
Results obtained indicate the excellent performance of the proposed approach.
arXiv Detail & Related papers (2021-10-24T11:38:47Z) - Interflow: Aggregating Multi-layer Feature Mappings with Attention
Mechanism [0.7614628596146599]
This paper proposes the Interflow algorithm specially for traditional CNN models.
Interflow divides CNNs into several stages according to the depth and makes predictions by the feature mappings in each stage.
It can alleviate gradient vanishing problem, lower the difficulty of network depth selection, and lighten possible over-fitting problem.
arXiv Detail & Related papers (2021-06-26T18:22:01Z) - CREPO: An Open Repository to Benchmark Credal Network Algorithms [78.79752265884109]
Credal networks are imprecise probabilistic graphical models based on, so-called credal, sets of probability mass functions.
A Java library called CREMA has been recently released to model, process and query credal networks.
We present CREPO, an open repository of synthetic credal networks, provided together with the exact results of inference tasks on these models.
arXiv Detail & Related papers (2021-05-10T07:31:59Z) - SLPC: a VRNN-based approach for stochastic lidar prediction and
completion in autonomous driving [63.87272273293804]
We propose a new LiDAR prediction framework that is based on generative models namely Variational Recurrent Neural Networks (VRNNs)
Our algorithm is able to address the limitations of previous video prediction frameworks when dealing with sparse data by spatially inpainting the depth maps in the upcoming frames.
We present a sparse version of VRNNs and an effective self-supervised training method that does not require any labels.
arXiv Detail & Related papers (2021-02-19T11:56:44Z) - Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model.
This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs)
The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
arXiv Detail & Related papers (2020-03-13T13:11:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.