Explainability in medical images analysis plays an important role in the accurate diagnosis and treatment of tumors, which can help medical professionals better understand the images analysis results based on deep models. This paper proposes an explainable brain tumor detection framework that can complete the tasks of segmentation, classification, and explainability. The re-parameterization method is applied to our classification network, and the effect of explainable heatmaps is improved by modifying the network architecture. Our classification model also has the advantage of post-hoc explainability. We used the BraTS-2018 dataset for training and verification. Experimental results show that our simplified framework has excellent performance and high calculation speed. The comparison of results by segmentation and explainable neural networks helps researchers better understand the process of the black box method, increase the trust of the deep model output, and make more accurate judgments in disease identification and diagnosis.

The human attention mechanism can be understood and simulated by closely associating the saliency prediction task to neuroscience and psychology. Furthermore, saliency prediction is widely used in computer vision and interdisciplinary subjects. In recent years, with the rapid development of deep learning, deep models have made amazing achievements in saliency prediction. Deep learning models can automatically learn features, thus solving many drawbacks of the classic models, such as handcrafted features and task settings, among others. Nevertheless, the deep models still have some limitations, for example in tasks involving multi-modality and semantic understanding. This study focuses on summarizing the relevant achievements in the field of saliency prediction, including the early neurological and psychological mechanisms and the guiding role of classic models, followed by the development process and data comparison of classic and deep saliency prediction models. This study also discusses the relationship between the model and human vision, as well as the factors that cause the semantic gaps, the influences of attention in cognitive research, the limitations of the saliency model, and the emerging applications, to provide new saliency predictions for follow-up work and the necessary help and advice.

Target tracking has always been a popular research area in computer vision, and many important methods have been proposed. However, most methods can only solve partial and slight occlusion. If the target is lost, a common solution is to keep detecting, reidentify the target when it reappears, and then link the broken tracks together, but this makes tracking discontinuous. There are two key points in this problem: continuous tracking and occlusion judgment. In this paper, we propose a target tracking method with a short-time prediction function to solve this problem. For continuous tracking, we establish a 3D dynamic model to estimate the motion state of the target in each frame. For occlusion judgment, we use a depth prediction network to estimate the depth of the target and then determine whether the target is occluded by the depth. Without relying on depth sensors or multiple cameras, we achieve depth estimation using only a single monocular image, which greatly expands the application of our method. Benefit from the introduction of motion estimation and depth prediction, the tracking accuracy of our method has been significantly improved, especially for better robustness to occlusion. Even when the target is completely occluded, it can be tracked for a short time without reidentification. In addition, we improve the speed of depth prediction through knowledge distillation by 2.08 times, and the final tracking speed reaches 52.6 Hz on GPU, which meets the real-time tracking requirements.

Deep saliency models can effectively imitate the attention mechanism of human vision, and they perform considerably better than classical models that rely on handcrafted features. However, deep models also require higher-level information, such as context or emotional content, to further approach human performance. Therefore, this study proposes a multilevel saliency prediction network that aims to use a combination of spatial and channel information to find possible high-level features, further improving the performance of a saliency model. Firstly, we use a VGG style network with an identity block as the primary network architecture. With the help of re-parameterization, we can obtain rich features similar to multiscale networks and effectively reduce computational cost. Secondly, a subnetwork with a channel attention mechanism is designed to find potential saliency regions and possible high-level semantic information in an image. Finally, image spatial features and a channel enhancement vector are combined after quantization to improve the overall performance of the model. Compared with classical models and other deep models, our model exhibits superior overall performance.

Target tracking is an important application of unmanned aerial vehicles (UAVs). The template is the identity of the target and has a great impact on the performance of target tracking. Most methods only keep the latest template of the target, which is intuitive and convenient but has poor ability to resist the change of target appearance, especially to reidentify a target that has disappeared for a long time. In this paper, we propose a practical multiobject tracking (MOT) method, which uses historical information of targets for better adapting to appearance variations during tracking. To preserve the spatial-temporal information of the target, we introduce a memory pool to store masked feature maps at different moments, and precise masks are generated by a segmentation network. Meanwhile, we fuse the feature maps at different moments by calculating the pixel-level similarity between the current feature map and the masked historical feature maps. Benefiting from the powerful segmentation features and the utilization of historical information, our method can generate more accurate bounding boxes of the targets. Extensive experiments and comparisons with many trackers on MOTS, MOT17, and MOT20 demonstrate that our method is competitive. The ablation study showed that the introduction of memory improves the multiobject tracking accuracy (MOTA) by 2.1.