Benchmark Object Detection (OD) datasets are essential for advancing computer vision in areas such as autonomous driving, robotics, and surveillance. MS-COCO has become the standard benchmark due to its object diversity and scene complexity. Despite the considerable time since its release, MS-COCO remains widely used, as many OD algorithms have been evaluated on it. However, it suffers from issues including missing or incorrect labels, inaccurate bounding boxes, duplicates, and inconsistent group labeling. These data quality problems are recognized as critical bottlenecks, motivating a data-centric shift that prioritizes improving datasets over simply tuning models. To address these challenges, we propose a comprehensive data refinement framework and present MJ-COCO, a newly re-annotated version of MS-COCO. Our approach combines loss and gradient-based error detection with a four-stage pseudo-labeling process: (1) bounding box generation via invertible transformations, (2) IoU-based duplicate removal and confidence merging, (3) class consistency verification through an expert recognizer, and (4) spatial adjustment using region activation maps. This pipeline enables scalable, accurate correction of annotation errors without manual re-labeling. Extensive experiments with one-stage (RetinaNet, YOLOv3, YOLOX) and two-stage (Faster R-CNN, Libra R-CNN) models across MS-COCO, Sama COCO, Objects365, and PASCAL VOC show that MJ-COCO consistently outperforms MS-COCO, particularly on high-quality validation sets, with notable improvements in Average Precision (AP) and AP S . Annotation coverage also improved significantly, with over 200,000 more small object annotations. These results confirm MJ-COCO as a more accurate, robust, and scalable alternative for modern OD tasks. Our annotations are publicly available at https://www.kaggle.com/datasets/mjcoco2025/mj-coco-2025 .

Vision-based fire detection systems have been significantly improved by deep models; however, higher numbers of false alarms and a slow inference speed still hinder their practical applicability in real-world scenarios. For a balanced trade-off between computational cost and accuracy, we introduce dual fire attention network (DFAN) to achieve effective yet efficient fire detection. The first attention mechanism highlights the most important channels from the features of an existing backbone model, yielding significantly emphasized feature maps. Then, a modified spatial attention mechanism is employed to capture spatial details and enhance the discrimination potential of fire and non-fire objects. We further optimize the DFAN for real-world applications by discarding a significant number of extra parameters using a meta-heuristic approach, which yields around 50% higher FPS values. Finally, we contribute a medium-scale challenging fire classification dataset by considering extremely diverse, highly similar fire/non-fire images and imbalanced classes, among many other complexities. The proposed dataset advances the traditional fire detection datasets by considering multiple classes to answer the following question: what is on fire? We perform experiments on four widely used fire detection datasets, and the DFAN provides the best results compared to 21 state-of-the-art methods. Consequently, our research provides a baseline for fire detection over edge devices with higher accuracy and better FPS values, and the proposed dataset extension provides indoor fire classes and a greater number of outdoor fire classes; these contributions can be used in significant future research. Our codes and dataset will be publicly available at https://github.com/tanveer-hussain/DFAN.

Skin cancer is actually considered one of the most harmful human types of cancer. It exists in many types, but melanoma is the most severe. Early detection of melanoma cancer is valuable for the treatment of patients. For this function, computer vision plays a major role in medical imaging for the diagnosis of cancer. Using Jetson Nano, we established an image processing method for skin cancer detection at the initial stage in the proposed work. The proposed research framework consists of five phases: a collection of dermoscopic images, grayscale conversion of an image, area of interest segmentation, and noise removal. Finally, the lesion features are extracted from the lesion and categorized into three groups with the aid of ABCD rules: benign, suspicious and malignant. On PH2 and ISIC data sets of skin lesion images, experiments are performed. Compared to those published in state of the art for skin cancer identification, the proposed method has shown better results.