In the recent era of AI, instance segmentation has significantly advanced boundary and object detection especially in diverse fields (e.g., biological and environmental research). Despite its progress, edge detection amid adjacent objects (e.g., organism cells) still remains intractable. This is because homogeneous and heterogeneous objects are prone to being mingled in a single image. To cope with this challenge, we propose the weighted Mask R-CNN designed to effectively separate overlapped objects in virtue of extra weights to adjacent boundaries. For numerical study, a range of experiments are performed with applications to simulated data and real data (e.g., Microcystis, one of the most common algae genera and cell membrane images). It is noticeable that the weighted Mask R-CNN outperforms the standard Mask R-CNN, given that the analytic experiments show on average 92.5% of precision and 96.4% of recall in algae data and 94.5% of precision and 98.6% of recall in cell membrane data. Consequently, we found that a majority of sample boundaries in real and simulated data are precisely segmented in the midst of object mixtures.

In this paper, we propose a robust and reliable face recognition model that incorporates depth information such as data from point clouds and depth maps into RGB image data to avoid false facial verification caused by face spoofing attacks while increasing the model’s performance. The proposed model is driven by the spatially adaptive convolution (SAC) block of SqueezeSegv3; this is the attention block that enables the model to weight features according to their importance of spatial location. We also utilize large-margin loss instead of softmax loss as a supervision signal for the proposed method, to enforce high discriminatory power. In the experiment, the proposed model, which incorporates depth information, had 99.88% accuracy and an F 1 score of 93.45%, outperforming the baseline models, which used RGB data alone.

Experience replay memory in reinforcement learning enables agents to remember and reuse past experiences. Most of the reinforcement models are subject to single experience replay memory to operate agents. In this article, we propose a framework that accommodates doubly used experience replay memory, exploiting both important transitions and new transitions simultaneously. In numerical studies, the deep Q -networks (DQN) equipped with double experience replay memory are examined under various scenarios. A self-driving car requires an automated agent to figure out when to adequately change lanes on the real-time basis. To this end, we apply our proposed agent to the simulation of urban mobility (SUMO) experiments. Besides, we also verify its applicability to reinforcement learning whose action space is discrete (e.g., computer game environments). Taken all together, we conclude that the proposed framework outperforms priorly known reinforcement learning models in the virtue of double experience replay memory.

Neural networks provide excellent service on recognition tasks such as image recognition and speech recognition as well as for pattern analysis and other tasks in fields related to artificial intelligence. However, neural networks are vulnerable to adversarial examples. An adversarial example is a sample that is designed to be misclassified by a target model, although it poses no problem for recognition by humans, that is created by applying a minimal perturbation to a legitimate sample. Because the perturbation applied to the legitimate sample to create an adversarial example is optimized, the classification score for the target class has the characteristic of being similar to that for the legitimate class. This regularity occurs because minimal perturbations are applied only until the classification score for the target class is slightly higher than that for the legitimate class. Given the existence of this regularity in the classification scores, it is easy to detect an optimized adversarial example by looking for this pattern. However, the existing methods for generating optimized adversarial examples do not consider their weakness of allowing detectability by recognizing the pattern in the classification scores. To address this weakness, we propose an optimized adversarial example generation method in which the weakness due to the classification score pattern is removed. In the proposed method, a minimal perturbation is applied to a legitimate sample such that the classification score for the legitimate class is less than that for some of the other classes, and an optimized adversarial example is created with the pattern vulnerability removed. The results show that using 500 iterations, the proposed method can generate an optimized adversarial example that has a 100% attack success rate, with distortions of 2.81 and 2.23 for MNIST and Fashion-MNIST, respectively.

No abstract