Shiyin Qin

Haruna Yunusa, Shiyin Qin, Abdulrahman Hamman Adama Chukkol et al.

The hybrid of Convolutional Neural Network (CNN) and Vision Transformers (ViT) architectures has emerged as a groundbreaking approach, pushing the boundaries of computer vision (CV). This comprehensive review provides a thorough examination of the literature on state-of-the-art hybrid CNN-ViT architectures, exploring the synergies between these two approaches. The main content of this survey includes: (1) a background on the vanilla CNN and ViT, (2) systematic review of various taxonomic hybrid designs to explore the synergy achieved through merging CNNs and ViTs models, (3) comparative analysis and application task-specific synergy between different hybrid architectures, (4) challenges and future directions for hybrid models, (5) lastly, the survey concludes with a summary of key findings and recommendations. Through this exploration of hybrid CV architectures, the survey aims to serve as a guiding resource, fostering a deeper understanding of the intricate dynamics between CNNs and ViTs and their collective impact on shaping the future of CV architectures.

Yunusa Haruna, Shiyin Qin, Abdulrahman Hamman Adama Chukkol et al.

Detecting objects across varying scales is still a challenge in computer vision, particularly in agricultural applications like Rice Leaf Disease (RLD) detection, where objects exhibit significant scale variations (SV). Conventional object detection (OD) like Faster R-CNN, SSD, and YOLO methods often fail to effectively address SV, leading to reduced accuracy and missed detections. To tackle this, we propose SaRPFF (Self-Attention with Register-based Pyramid Feature Fusion), a novel module designed to enhance multi-scale object detection. SaRPFF integrates 2D-Multi-Head Self-Attention (MHSA) with Register tokens, improving feature interpretability by mitigating artifacts within MHSA. Additionally, it integrates efficient attention atrous convolutions into the pyramid feature fusion and introduce a deconvolutional layer for refined up-sampling. We evaluate SaRPFF on YOLOv7 using the MRLD and COCO datasets. Our approach demonstrates a +2.61% improvement in Average Precision (AP) on the MRLD dataset compared to the baseline FPN method in YOLOv7. Furthermore, SaRPFF outperforms other FPN variants, including BiFPN, NAS-FPN, and PANET, showcasing its versatility and potential to advance OD techniques. This study highlights SaRPFF effectiveness in addressing SV challenges and its adaptability across FPN-based OD models.

Bilal Hassan, Taimur Hassan, Ramsha Ahmed et al.

This paper proposes an automated method for the segmentation and extraction of the posterior segment of the human eye, including the vitreous, retina, choroid, and sclera compartments, using multi-vendor optical coherence tomography (OCT) scans. The proposed method works in two phases. First extracts the retinal pigment epithelium (RPE) layer by applying the adaptive thresholding technique to identify the retina-choroid junction. Then, it exploits the structure tensor guided approach to extract the inner limiting membrane (ILM) and the choroidal stroma (CS) layers, locating the vitreous-retina and choroid-sclera junctions in the candidate OCT scan. Furthermore, these three junction boundaries are utilized to conduct posterior eye compartmentalization effectively for both healthy and disease eye OCT scans. The proposed framework is evaluated over 1000 OCT scans, where it obtained the mean intersection over union (IoU) and mean Dice similarity coefficient (DSC) scores of 0.874 and 0.930, respectively.