Topic
Corner case
About: Corner case is a research topic. Over the lifetime, 64 publications have been published within this topic receiving 1020 citations.
Papers published on a yearly basis
Papers
14 Oct 2017
TL;DR: DeepXplore efficiently finds thousands of incorrect corner case behaviors in state-of-the-art DL models with thousands of neurons trained on five popular datasets including ImageNet and Udacity self-driving challenge data.
Abstract: Deep learning (DL) systems are increasingly deployed in safety- and security-critical domains including self-driving cars and malware detection, where the correctness and predictability of a system's behavior for corner case inputs are of great importance Existing DL testing depends heavily on manually labeled data and therefore often fails to expose erroneous behaviors for rare inputs We design, implement, and evaluate DeepXplore, the first whitebox framework for systematically testing real-world DL systems First, we introduce neuron coverage for systematically measuring the parts of a DL system exercised by test inputs Next, we leverage multiple DL systems with similar functionality as cross-referencing oracles to avoid manual checking Finally, we demonstrate how finding inputs for DL systems that both trigger many differential behaviors and achieve high neuron coverage can be represented as a joint optimization problem and solved efficiently using gradient-based search techniques DeepXplore efficiently finds thousands of incorrect corner case behaviors (eg, self-driving cars crashing into guard rails and malware masquerading as benign software) in state-of-the-art DL models with thousands of neurons trained on five popular datasets including ImageNet and Udacity self-driving challenge data For all tested DL models, on average, DeepXplore generated one test input demonstrating incorrect behavior within one second while running only on a commodity laptop We further show that the test inputs generated by DeepXplore can also be used to retrain the corresponding DL model to improve the model's accuracy by up to 3%
1,171 citations
9 Jun 2019
TL;DR: This paper provides a formal definition of a corner case and proposes a system framework for both the online and the offline use case that can handle video signals from front cameras of a naturally moving vehicle and can output a corners case score.
Abstract: The progress in autonomous driving is also due to the increased availability of vast amounts of training data for the underlying machine learning approaches. Machine learning systems are generally known to lack robustness, e.g., if the training data did rarely or not at all cover critical situations. The challenging task of corner case detection in video, which is also somehow related to unusual event or anomaly detection, aims at detecting these unusual situations, which could become critical, and to communicate this to the autonomous driving system (online use case). Such a system, however, could be also used in offline mode to screen vast amounts of data and select only the relevant situations for storing and (re)training machine learning algorithms. So far, the approaches for corner case detection have been limited to videos recorded from a fixed camera, mostly for security surveillance. In this paper, we provide a formal definition of a corner case and propose a system framework for both the online and the offline use case that can handle video signals from front cameras of a naturally moving vehicle and can output a corner case score.
117 citations
19 Oct 2020
TL;DR: This paper provides a systematization of corner cases for visual perception in automated driving, with the categories being structured by detection complexity.
Abstract: One major task in automated driving is the development of robust and safe visual perception modules. It is of utmost importance that visual perception reacts adequately to so-called corner cases, which range from overexposure of the image sensor to unexpected and potentially dangerous traffic situations. Their detection thus has high significance both as an online system in the intelligent vehicle, but also in the extraction of relevant training and test data for perception modules. In this paper, we provide a systematization of corner cases for visual perception in automated driving, with the categories being structured by detection complexity. Furthermore, we discuss existing metrics and datasets which can be used for the evaluation of corner case detection methods depending on their suitability to provide beneficial information for the various categories.
83 citations
24 Jun 2019
TL;DR: This work proposes and implements Deep Validation, a novel framework for detecting real-world error-inducing corner cases in a DNN-based system during runtime, and model the specifications of DNNs by resorting to their training data and cast checking input validity of Dnns as the problem of discrepancy estimation.
Abstract: The exceptional performance of Deep neural networks (DNNs) encourages their deployment in safety-and dependability-critical systems. However, DNNs often demonstrate erroneous behaviors in real-world corner cases. Existing countermeasures center on improving the testing and bug-fixing practice. Unfortunately, building a bug-free DNN-based system is almost impossible currently due to its black-box nature, so anomaly detection is imperative in practice. Motivated by the idea of data validation in a traditional program, we propose and implement Deep Validation, a novel framework for detecting real-world error-inducing corner cases in a DNN-based system during runtime. We model the specifications of DNNs by resorting to their training data and cast checking input validity of DNNs as the problem of discrepancy estimation. Deep Validation achieves excellent detection results against various corner case scenarios across three popular datasets. Consequently, Deep Validation greatly complements existing efforts and is a crucial step toward building safe and dependable DNN-based systems.
54 citations
19 Oct 2008
TL;DR: A multithreaded multiprocessors platform and multimedia application is presented and corner case coverage can now be supplied with a very high accuracy, allowing to quickly investigate architectural alternatives.
Abstract: Formal performance analysis is now regularly applied in the design of distributed embedded systems such as automotive electronics, where it greatly contributes to an improved predictability and platform robustness of complex networked systems. Even though it might be highly beneficial also in MpSoC design, formal performance analysis could not easily be applied so far, because the classical task communication model does not cover processor-memory traffic, which is an integral part of MpSoC timing. Introducing memory accesses as individual transactions under the classical model has shown to be inefficient, and previous approaches work well only under strict orthogonalization of different traffic streams.Recent research has presented extensions of the classical task model and a corresponding analysis that covers performance implications of shared memory traffic. In this paper we present a multithreaded multiprocessors platform and multimedia application. We conduct performance analysis using the new analysis options and specifically benchmark the quality of the available approach. Our experiments show that corner case coverage can now be supplied with a very high accuracy, allowing to quickly investigate architectural alternatives.
49 citations
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2021 | 11 |
| 2020 | 5 |
| 2019 | 7 |
| 2018 | 5 |
| 2017 | 1 |
| 2016 | 2 |