Na Dong

Xiao Li, Yining Liu, Na Dong et al.

Deep learning-based object recognition systems can be easily fooled by various adversarial perturbations. One reason for the weak robustness may be that they do not have part-based inductive bias like the human recognition process. Motivated by this, several part-based recognition models have been proposed to improve the adversarial robustness of recognition. However, due to the lack of part annotations, the effectiveness of these methods is only validated on small-scale nonstandard datasets. In this work, we propose PIN++, short for PartImageNet++, a dataset providing high-quality part segmentation annotations for all categories of ImageNet-1K (IN-1K). With these annotations, we build part-based methods directly on the standard IN-1K dataset for robust recognition. Different from previous two-stage part-based models, we propose a Multi-scale Part-supervised Model (MPM), to learn a robust representation with part annotations. Experiments show that MPM yielded better adversarial robustness on the large-scale IN-1K over strong baselines across various attack settings. Furthermore, MPM achieved improved robustness on common corruptions and several out-of-distribution datasets. The dataset, together with these results, enables and encourages researchers to explore the potential of part-based models in more real applications.

Na Dong, Yongqiang Zhang, Mingli Ding et al.

Deep networks have shown remarkable results in the task of object detection. However, their performance suffers critical drops when they are subsequently trained on novel classes without any sample from the base classes originally used to train the model. This phenomenon is known as catastrophic forgetting. Recently, several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection. Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novel classes. This requirement is impractical in many real-world settings since the base classes do not necessarily co-occur with the novel classes. In view of this limitation, we consider a more practical setting of complete absence of co-occurrence of the base and novel classes for the object detection task. We propose the use of unlabeled in-the-wild data to bridge the non co-occurrence caused by the missing base classes during the training of additional novel classes. To this end, we introduce a blind sampling strategy based on the responses of the base-class model and pre-trained novel-class model to select a smaller relevant dataset from the large in-the-wild dataset for incremental learning. We then design a dual-teacher distillation framework to transfer the knowledge distilled from the base- and novel-class teacher models to the student model using the sampled in-the-wild data. Experimental results on the PASCAL VOC and MS COCO datasets show that our proposed method significantly outperforms other state-of-the-art class-incremental object detection methods when there is no co-occurrence between the base and novel classes during training.

Na Dong, Meng-die Zhai, Jian-fang Chang et al.

This paper proposes a novel automatic classification framework for the recognition of five types of white blood cells. Segmenting complete white blood cells from blood smears images and extracting advantageous features from them remain challenging tasks in the classification of white blood cells. Therefore, we present an adaptive threshold segmentation method to deal with blood smears images with non-uniform color and uneven illumination, which is designed based on color space information and threshold segmentation. Subsequently, after successfully separating the white blood cell from the blood smear image, a large number of nonlinear features including geometrical, color and texture features are extracted. Nevertheless, redundant features can affect the classification speed and efficiency, and in view of that, a feature selection algorithm based on classification and regression trees (CART) is designed. Through in-depth analysis of the nonlinear relationship between features, the irrelevant and redundant features are successfully removed from the initial nonlinear features. Afterwards, the selected prominent features are fed into particle swarm optimization support vector machine (PSO-SVM) classifier to recognize the types of the white blood cells. Finally, to evaluate the performance of the proposed white blood cell classification methodology, we build a white blood cell data set containing 500 blood smear images for experiments. By comparing with the ground truth obtained manually, the proposed segmentation method achieves an average of 95.98% and 97.57% dice similarity for segmented nucleus and cell regions respectively. Furthermore, the proposed methodology achieves 99.76% classification accuracy, which well demonstrates its effectiveness.

Na Dong, Wen-qi Zhang, Zhong-ke Gao

Brain-controlled unmanned aerial vehicle (uav) is a uav that can analyze human brain electrical signals through BCI to obtain flight commands. The research of brain-controlled uav can promote the integration of brain-computer and has a broad application prospect. At present, BCI still has some problems, such as limited recognition accuracy, limited recognition time and small number of recognition commands in the acquisition of control commands by analyzing eeg signals. Therefore, the control performance of the quadrotor which is controlled only by brain is not ideal. Based on the concept of Shared control, this paper designs an assistant controller using fuzzy PID control, and realizes the cooperative control between automatic control and brain control. By evaluating the current flight status and setting the switching rate, the switching mechanism of automatic control and brain control can be decided to improve the system control performance. Finally, a rectangular trajectory tracking control experiment of the same height is designed for small quadrotor to verify the algorithm.

Na Dong, Wen-qi Zhang, Zhong-ke Gao

Brain controlled vehicle refers to the vehicle that obtains control commands by analyzing the driver's EEG through Brain-Computer Interface (BCI). The research of brain controlled vehicles can not only promote the integration of brain machines, but also expand the range of activities and living ability of the disabled or some people with limited physical activity, so the research of brain controlled vehicles is of great significance and has broad application prospects. At present, BCI has some problems such as limited recognition accuracy, long recognition time and limited number of recognition commands in the process of analyzing EEG signals to obtain control commands. If only use the driver's EEG signals to control the vehicle, the control performance is not ideal. Based on the concept of Shared control, this paper uses the fuzzy control (FC) to design an auxiliary controller to realize the cooperative control of automatic control and brain control. Designing a Shared controller which evaluates the current vehicle status and decides the switching mechanism between automatic control and brain control to improve the system control performance. Finally, based on the joint simulation platform of Carsim and MATLAB, with the simulated brain control signals, the designed experiment verifies that the control performance of the brain control vehicle can be improved by adding the auxiliary controller.