MIAFEx: An Attention-based Feature Extraction Method for Medical Image Classification

Feature extraction techniques are crucial in medical image classification; however, classical feature extractors in addition to traditional machine learning classifiers often exhibit significant limitations in providing sufficient discriminative information for complex image sets. While Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) have shown promise in feature extraction, they are prone to overfitting due to the inherent characteristics of medical imaging data, including small sample sizes or high intra-class variance. In this work, the Medical Image Attention-based Feature Extractor (MIAFEx) is proposed, a novel method that employs a learnable refinement mechanism to enhance the classification token within the Transformer encoder architecture. This mechanism adjusts the token based on learned weights, improving the extraction of salient features and enhancing the model's adaptability to the challenges presented by medical imaging data. The MIAFEx output features quality is compared against classical feature extractors using traditional and hybrid classifiers. Also, the performance of these features is compared against modern CNN and ViT models in classification tasks, demonstrating its superiority in accuracy and robustness across multiple complex classification medical imaging datasets. This advantage is particularly pronounced in scenarios with limited training data, where traditional and modern models often struggle to generalize effectively. The source code of this proposal can be found at https://github.com/Oscar-RamosS/Medical-Image-Attention-based-Feature-Extractor-MIAFEx

UNIR-Net: A Novel Approach for Restoring Underwater Images with Non-Uniform Illumination Using Synthetic Data

Enhancing underwater images with non-uniform illumination (NUI) is crucial for improving visibility and visual quality in marine environments, where image degradation is caused by significant absorption and scattering effects. However, traditional model-based methods are often ineffective at capturing the complex illumination variations present in such images, resulting in limited visual improvements. On the other hand, learning-based approaches have shown promising results but face challenges due to the lack of specific datasets designed to effectively address the non-uniform illumination problem. To overcome these challenges, the Underwater Non-uniform Illumination Restoration Network (UNIR-Net) is introduced, a novel method that integrates illumination enhancement and attention blocks, along with visual refinement and contrast correction modules. This approach is specifically designed to mitigate the scattering and absorption effects that cause light attenuation in underwater environments. Additionally, the Paired Underwater Non-uniform Illumination (PUNI) dataset is presented, a paired resource that facilitates the restoration of underwater images under non-uniform illumination conditions. Extensive experiments conducted on the PUNI dataset and the large-scale real-world Non-Uniform Illumination Dataset (NUID), which contains underwater images with non-uniform illumination, demonstrate the robust generalization ability of UNIR-Net. This method outperforms existing approaches in both quantitative metrics and qualitative evaluations. Furthermore, UNIR-Net not only significantly enhances the visual quality of images but also improves performance in advanced computer vision tasks, such as semantic segmentation in underwater environments, highlighting its broad applicability and potential impact. The code of this method is available at https://github.com/xingyumex/UNIR-Net

ALEN: A Dual-Approach for Uniform and Non-Uniform Low-Light Image Enhancement

Low-light image enhancement is an important task in computer vision, essential for improving the visibility and quality of images captured in non-optimal lighting conditions. Inadequate illumination can lead to significant information loss and poor image quality, impacting various applications such as surveillance. photography, or even autonomous driving. In this regard, automated methods have been developed to automatically adjust illumination in the image for a better visual perception. Current enhancement techniques often use specific datasets to enhance low-light images, but still present challenges when adapting to diverse real-world conditions, where illumination degradation may be localized to specific regions. To address this challenge, the Adaptive Light Enhancement Network (ALEN) is introduced, whose main approach is the use of a classification mechanism to determine whether local or global illumination enhancement is required. Subsequently, estimator networks adjust illumination based on this classification and simultaneously enhance color fidelity. ALEN integrates the Light Classification Network (LCNet) for illuminance categorization, complemented by the Single-Channel Network (SCNet), and Multi-Channel Network (MCNet) for precise estimation of illumination and color, respectively. Extensive experiments on publicly available datasets for low-light conditions were carried out to underscore ALEN's robust generalization capabilities, demonstrating superior performance in both quantitative metrics and qualitative assessments when compared to recent state-of-the-art methods. The ALEN not only enhances image quality in terms of visual perception but also represents an advancement in high-level vision tasks, such as semantic segmentation, as presented in this work. The code of this method is available at https://github.com/xingyumex/ALEN.