In the autonomous driving environment, object instances in an image can be affected by various factors such as camera, driving state, weather, and system component. However, the deep learning-based vision systems are vulnerable to perturbation, which contains noise. Thus, robust object detection under harsh autonomous-driving environments is a more difficult than the generic situation. In this paper, it is found that not only the accuracy, but also the speed of the non-maximum suppression-based detector can be degraded under harsh environments. Therefore, object detection is handled under a harsh situation with adversarial mechanisms such as adversarial training and adversarial defence. Adversarial defence modules are designed to improve robustness in feature extraction level and define perturbations under a harsh environment for training object detectors to improve the robustness of the model's decision boundary. The proposed adversarial defence and training mechanisms improve the object detector in both accuracy and speed. The proposed method shows a 43.7% mean average precision for the COCO2015 dataset in generic object detection and 39.0% mean average precision for the BDD100K dataset in a driving environment. Furthermore, it achieves a real-time capability of 23 frames per second. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Ensemble method has been shown a great success for 2D image segmentation, while 3D brain segmentation has received less attention using 2D pre-trained model. In this work, we present various 2D ensemble methods to utilize the 2D pre-trained models for the brain MRI segmentation task using given small medical 3D data. We perform a series of experiments by comparing several 2D single pre-trained models to build and analyze the various 2D ensemble methods. We evaluate the ensemble methods against 3D single scratch model in terms of accuracy, time, and crop size. In addition, we investigate the relationship between different compositions of train data and performance for semantic segmentation using MRBrainS18 train dataset. Experimental results demonstrate a significant improvement of the proposed ensemble method in comparison with existing methods using 3D CNN models for brain MRI segmentation.
Despite increasing interest in developing interpretable machine learning methods, most recent studies have provided explanations only for single instances, require additional datasets, and are sensitive to hyperparameters. This paper proposes a confusion graph that reveals model weaknesses by constructing a confusion dictionary. Unlike other methods, which focus on the performance variation caused by single-neuron suppression, it defines the role of each neuron in two different perspectives: ‘correction’ and ‘violation.’ Furthermore, our method can identify the class relationships in similar positions at the feature level, which can suggest improvements to the model. Finally, the proposed graph construction is model-agnostic and does not require additional data or tedious hyperparameter tuning. Experimental results show that the information loss from omitting the channels guided by the proposed graph can result in huge performance degradation, from 91% to 33%, while the proposed graph only retains 1% of total neurons.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.