In the field of computer vision, semantic segmentation became an important problem that has applications in fields such as autonomous driving and robotics. Image segmentation datasets, on the other hand, present substantial hurdles due to the high intra-class variability, which includes differences across car models or building designs, and the low inter-class variability, which makes it difficult to discern between objects such as buildings that have facades that are visually identical. A focus-enhanced ASPP module that is coupled with an upgraded backbone for semantic segmentation networks is presented in this study as a solution to the problems that have been identified. In order to augment the adaptability of extracted features, the proposed framework utilizes the capability of an attention ASPP module to implement attention processes within the multiscale module. In order to efficiently capture complex features, the encoder stage also makes use of a ResNet-50 backbone that has been properly optimized. In addition, to increase the robustness of the model, data augmentation approaches are applied. mDice of 87.82, mIoU of 79.05, and mean accuracy of 85.2 on the Stanford dataset, and mDice of 88.91, mIoU of 80.03, and mean accuracy of 89.84 on the Cityscapes dataset, according to experimental assessments, demonstrate that the developed technique performs at an accuracy level that is believed to be modern. As a result of these findings, the possibility for greatly improving semantic segmentation performance may be highlighted by integrating attention mechanisms, ASPP modules, and upgraded ResNet structures.

This study explores the use of efficient deep learning algorithms for segmenting lower grade gliomas (LGG) in medical images. It evaluates various pre-trained Atrous-Convolutional architectures and U-Nets, proposing a novel transformer-based approach that surpasses traditional methods. DeepLabV3+ with MobileNetV3 backbone achieved the best results among pre-trained models, but the transformer-based approach excelled with superior segmentation accuracy and efficiency. Transfer learning significantly enhanced model performance on the LGG dataset, even with limited training samples, emphasizing the importance of selecting appropriate pre-trained models. The transformer-based method offers advantages such as efficient memory usage, better generalization, and the ability to process images of arbitrary sizes, making it suitable for clinical applications. These findings suggest that advanced deep learning techniques can improve diagnostic tools for LGG and potentially other cancers, highlighting the transformative impact of deep learning and transfer learning in medical image segmentation.

Deep Convolutional neural networks (CNNs) have attained remarkable success in numerous visual recognition tasks. There are two challenges when adopting CNNs in real-world applications: a) Existing CNNs are computationally expensive and memory intensive, impeding their use in edge computing; b) there is no standard methodology for designing the CNN architecture for the intended problem. Network pruning/compression has emerged as a research direction to address the first challenge, and it has proven to moderate CNN computational load successfully. For the second challenge, various evolutionary algorithms have been proposed thus far. The algorithm proposed in this paper can be viewed as a solution to both challenges. Instead of using constant predefined criteria to evaluate the filters of CNN layers, the proposed algorithm establishes evaluation criteria in online manner during network training based on the combination of each filter’s profit in its layer and the next layer. In addition, the novel method suggested that it inserts new filters into the CNN layers. The proposed algorithm is not simply a pruning strategy but determines the optimal number of filters. Training on multiple CNN architectures allows us to demonstrate the efficacy of our approach empirically. Compared to current pruning algorithms, our algorithm yields a network with a remarkable prune ratio and accuracy. Despite the relatively high computational cost of an epoch in the proposed algorithm in pruning, altogether it achieves the resultant network faster than other algorithms.

Object tracking through multiple cameras is a popular research topic in security and surveillance systems especially when human objects are the target. However, occlusion is one of the challenging problems for the tracking process. This paper proposes a multiple-camera-based cooperative tracking method to overcome the occlusion problem. The paper presents a new model for combining Convolutional neural networks (CNNs), which allows the proposed method to learn the features with high discriminative power and geometrical independence. In the training phase, the CNNs are first pre-trained in each of the camera views, and a Convolutional gating network (CGN) is simultaneously pre-trained to produce a weight for each CNN output. The CNNs are then transferred to the tracking task where the pre-trained parameters of the CNNs are re-trained by using the data from the tracking phase. The weights obtained from the CGN are used in order to fuse the features learnt by the CNNs and the resulting weighted combination of the features is employed to represent the objects. Finally, the particle filter is used in order to track objects. The experimental results showed the efficiency of the proposed method in this paper.