Monitoring Object Detection Abnormalities via Data-Label and Post-Algorithm Abstractions

  title={Monitoring Object Detection Abnormalities via Data-Label and Post-Algorithm Abstractions},
  author={Yuhang Chen and Chih-Hong Cheng and Jun Yan and Rongjie Yan},
  journal={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
While object detection modules are essential functionalities for any autonomous vehicle, the performance of such modules that are implemented using deep neural networks can be, in many cases, unreliable. In this paper, we develop abstraction-based monitoring as a logical framework for filtering potentially erroneous detection results. Concretely, we consider two types of abstraction, namely data-label abstraction and post-algorithm abstraction. Operated on the training dataset, the construction… 

Figures and Tables from this paper

Into the unknown: Active monitoring of neural networks

This work proposes an algorithmic framework for active monitoring of neural-network classifiers that allows for their deployment in dynamic environments where unknown input classes appear frequently, and adjusts the framework to novel inputs incrementally, thereby improving short-term reliability of the classification.

Delft University of Technology Active Monitoring of Neural Networks

An algorithmic framework for monitoring reliability of a neural network and a monitor wrapped in this framework operates in parallel with the classifier, communicates interpretable labeling queries to the human user, and incrementally adapts to their feedback.



Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

This paper proposes to handle unreliable detection by collecting candidates from outputs of both detection and tracking, and adopts a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of the tracker.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

Simple online and realtime tracking with a deep association metric

This paper integrates appearance information to improve the performance of SORT and reduces the number of identity switches, achieving overall competitive performance at high frame rates.

Outside the Box: Abstraction-Based Monitoring of Neural Networks

A framework to monitor a neural network by observing the hidden layers is proposed, which employs a common abstraction from program analysis - boxes - to identify novel behaviors in the monitored layers, i.e., inputs that cause behaviors outside the box.

Improving Reliability of Object Detection for Lunar Craters Using Monte Carlo Dropout

In the convolutional neural network, the precision of prediction in lunar crater detection was improved by 2.1% by rejecting a prediction result with high variance as a false positive compared with the variance when predicting the training data.

Are we ready for autonomous driving? The KITTI vision benchmark suite

The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world.

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

A unified implementation of the Faster R-CNN, R-FCN and SSD systems is presented and the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures is traced out.

Runtime Monitoring Neuron Activation Patterns

For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runtime neuron

High-Speed Tracking with Kernelized Correlation Filters

A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

A simple baseline that utilizes probabilities from softmax distributions is presented, showing the effectiveness of this baseline across all computer vision, natural language processing, and automatic speech recognition, and it is shown the baseline can sometimes be surpassed.