We propose a novel method that combines the strengths of two popular class activation mapping techniques, GradCAM++ and ScoreCAM, to improve the interpretability and localization of convolutional neural networks (CNNs). Our proposed method, called “Grad++-ScoreCAM”, first utilizes the GradCAM++ algorithm to generate a coarse heatmap of an input image, highlighting the regions of importance for a particular class. Then, we employ the ScoreCAM algorithm to refine the heatmap by incorporating the localization information from the intermediate layers of the network. By combining these two techniques, we can generate more accurate and fine-grained heatmaps that highlight the regions of the input image that are most relevant to the prediction of the CNN. We evaluate our proposed method on a benchmark dataset and demonstrate its superiority over existing methods in terms of accuracy and interpretability. Our method has potential applications in various fields, including medical imaging, object recognition, and natural language processing.

Surveillance videos are crucial for crime prevention and public safety, yet the challenge of defining abnormal events hinders their effectiveness, limiting the applicability of supervised methods. This paper introduces an unsupervised end-to-end architecture for video anomaly detection that applies spatial and temporal features to identify anomalies in surveillance footage. The model employs a three-dimensional (3D) convolutional autoencoder, with an encoder-decoder structure that learns spatiotemporal representations and reconstructs the input through the latent space. Skip connections linking the encoder and decoder blocks facilitate the transfer of information across various scales of feature representations, enhancing the reconstruction process and improving the overall performance. The architecture incorporates spatial attention modules that highlight informative regions in the input, enabling improved anomaly detection. Spatial and contextual dependencies are further acquired using 3D convolutional filters. The performance of the proposed model is assessed on four benchmark datasets: UCSD Pedestrian 1, UCSD Pedestrian 2, CUHK Avenue, and ShanghaiTech. Notably, the proposed model achieves frame-based Area Under the Curve (AUC) scores of 94.6% on UCSD Ped 1, 96.7% on UCSD Ped 2, 84.7% on CUHK Avenue, and 74.8% on ShanghaiTech. These results demonstrate the state-of-the-art performance of the proposed approach, highlighting its efficacy in real-world anomaly detection scenarios.

Fashion image analysis has attracted significant research attention owing to the availability of large-scale fashion datasets with rich annotations. However, existing deep learning models for fashion datasets often have high computational requirements. In this study, we propose a new model suitable for low-power devices. The proposed network is a one-stage detector that rapidly detects multiple cloths and landmarks in fashion images. The network is designed as a modification of the EfficientDet originally proposed by Google Brain. The proposed network simultaneously trains the core input features with different resolutions and applies compound scaling to the backbone feature network. The bounding box/class/landmark prediction networks maintain the balance between the speed and accuracy. Moreover, a low number of parameters and low computational cost make it efficient. Without image preprocessing, we achieved 0.686 mean average precision (mAP) in the bounding box detection and 0.450 mAP in the landmark estimation on the DeepFashion2 validation dataset with an inference time of 42 ms. We obtained optimal results in extensive experiments with loss functions and optimizers. Furthermore, the proposed method has the advantage of operating in low-power devices.

Active contour models have achieved prominent success in the area of image segmentation, allowing complex objects to be segmented from the background for further analysis. Existing models can be divided into region-based active contour models and edge-based active contour models. However, both models use direct image data to achieve segmentation and face many challenging problems in terms of the initial contour position, noise sensitivity, local minima and inefficiency owing to the in-homogeneity of image intensities. The saliency map of an image changes the image representation, making it more visual and meaningful. In this study, we propose a novel model that uses the advantages of a saliency map with local image information (LIF) and overcomes the drawbacks of previous models. The proposed model is driven by a saliency map of an image and the local image information to enhance the progress of the active contour models. In this model, the saliency map of an image is first computed to find the saliency driven local fitting energy. Then, the saliency-driven local fitting energy is combined with the LIF model, resulting in a final novel energy functional. This final energy functional is formulated through a level set formulation, and regulation terms are added to evolve the contour more precisely across the object boundaries. The quality of the proposed method was verified on different synthetic images, real images and publicly available datasets, including medical images. The image segmentation results, and quantitative comparisons confirmed the contour initialization independence, noise insensitivity, and superior segmentation accuracy of the proposed model in comparison to the other segmentation models.

Noise or artifacts in an image, such as shadow artifacts, deteriorate the performance of state-of-the-art models for the segmentation of an image. In this study, a novel saliency-based region detection and image segmentation (SRIS) model is proposed to overcome the problem of image segmentation in the existence of noise and intensity inhomogeneity. Herein, a novel adaptive level-set evolution protocol based on the internal and external functions is designed to eliminate the initialization sensitivity, thereby making the proposed SRIS model robust to contour initialization. In the level-set energy function, an adaptive weight function is formulated to adaptively alter the intensities of the internal and external energy functions based on image information. In addition, the sign of energy function is modulated depending on the internal and external regions to eliminate the effects of noise in an image. Finally, the performance of the proposed SRIS model is illustrated on complex real and synthetic images and compared with that of the previously reported state-of-the-art models. Moreover, statistical analysis has been performed on coronavirus disease (COVID-19) computed tomography images and THUS10000 real image datasets to confirm the superior performance of the SRIS model from the viewpoint of both segmentation accuracy and time efficiency. Results suggest that SRIS is a promising approach for early screening of COVID-19.

Image segmentation is a tedious task that suffers from constraints, such as blurred or weak edges and intensity inhomogeneity. Active contour models, including edge-based and region-based methods, are extensively used for image segmentation. Each of these methods has its pros and cons that affect image-segmentation accuracy and CPU processing time. This study combines local and global region-based fitting energies and uses statistical image information to drag contours toward object boundaries, thus overcoming image inhomogeneity. The bias field, the region affected by image artefacts, is calculated and added with the local fitting energy model to capture inhomogeneous object boundaries. Furthermore, the combined local and global statistical information is appended with the edge-indicator function to rapidly move the contour over objects with strong edges, thereby avoiding boundary leakage. A region-based length term is driven by the signed pressure force function that evolves the curve on either the outer or inner side of the object, depending on its sign. The signed pressure force function contributes to achieving a smoother version of energy minimization over gradient descent flow. The proposed active contour model is applied to multiple synthetically generated, and medical images, together with online available public databases: the PH ² database, the skin-cancer-mnist-ham10000 THUS10000 database and the specific images from PascalVOC2007 database [1]. All the experiments confirm the better segmentation accuracy and improved time potency of the proposed methodology over previous level set-based approaches.