Convolutional neural networks (CNNs) have achieved state-of-the-art performance in numerous aspects of human life and the agricultural sector is no exception. One of the main objectives of deep learning for smart farming is to identify the precise location of weeds and crops on farmland. In this paper, we propose a semantic segmentation method based on a cascaded encoder-decoder network, namely CED-Net, to differentiate weeds from crops. The existing architectures for weeds and crops segmentation are quite deep, with millions of parameters that require longer training time. To overcome such limitations, we propose an idea of training small networks in cascade to obtain coarse-to-fine predictions, which are then combined to produce the final results. Evaluation of the proposed network and comparison with other state-of-the-art networks are conducted using four publicly available datasets: rice seeding and weed dataset, BoniRob dataset, carrot crop vs. weed dataset, and a paddy–millet dataset. The experimental results and their comparisons proclaim that the proposed network outperforms state-of-the-art architectures, such as U-Net, SegNet, FCN-8s, and DeepLabv3, over intersection over union (IoU), F1-score, sensitivity, true detection rate, and average precision comparison metrics by utilizing only (1/5.74 × U-Net), (1/5.77 × SegNet), (1/3.04 × FCN-8s), and (1/3.24 × DeepLabv3) fractions of total parameters.

Supervised semantic segmentation algorithms have been a hot area of exploration recently, but now the attention is being drawn towards completely unsupervised semantic segmentation. In an unsupervised framework, neither the targets nor the ground truth labels are provided to the network. That being said, the network is unaware about any class instance or object present in the given data sample. So, we propose a convolutional neural network (CNN) based architecture for unsupervised segmentation. We used the squeeze and excitation network, due to its peculiar ability to capture the features’ interdependencies, which increases the network’s sensitivity to more salient features. We iteratively enable our CNN architecture to learn the target generated by a graph-based segmentation method, while simultaneously preventing our network from falling into the pit of over-segmentation. Along with this CNN architecture, image enhancement and refinement techniques are exploited to improve the segmentation results. Our proposed algorithm produces improved segmented regions that meet the human level segmentation results. In addition, we evaluate our approach using different metrics to show the quantitative outperformance.

Few-shot anomaly detection in medical imaging remains challenging due to the scarcity of labeled abnormal samples and the need for robust feature representations. We propose AnomaMed, a novel multi-scale feature and prompt learning framework that extends Contrastive Language-Image Pretraining (CLIP) for medical anomaly detection. We introduce Prompt Feature Fusion Modules, which integrate multi-scale image and prompt feature fusion at different layers of a pretrained CLIP model, enabling hierarchical feature refinement for improved anomaly localization. Additionally, we incorporate self-attention-based prompt learning, dynamically refining textual representations to enhance text-image alignment in few-shot settings. To further improve generalization, we introduce the Artificial Anomaly Blending Module (AABM), which synthetically generates diverse medical anomalies, enabling the model to learn a broader range of pathological patterns. We evaluate AnomaMed on three benchmark medical imaging datasets, demonstrating state-of-the-art performance over existing vision-language models for few-shot anomaly detection. Results confirm that AnomaMed significantly improves anomaly detection and localization, validating the effectiveness of multi-scale feature fusion, self-attentive prompt learning, and synthetic anomaly augmentation.