Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification

A recent study has introduced a radiation-preserving imaging policy for pediatric hip dysplasia, utilizing an ultrasound-first approach that minimizes the need for radiographs. The method involves pretraining modality-specific encoders and calibrating a conformal deferral rule to ensure accurate predictions of key hip measurements, such as Graf alpha and acetabular index.

A new study introduces the Extracted Morphological Feature Engineered (EMFE) pipeline, a lightweight machine learning approach for malaria classification that achieves performance levels comparable to deep learning models while requiring significantly less computational power. This method utilizes the NIH Malaria Cell Images dataset, focusing on simple cell morphology features such as non-background pixels and holes within cells.

A new framework named DE-KAN has been introduced, utilizing a Dual Encoder Kolmogorov Arnold Network to enhance the accuracy of 2D teeth segmentation from panoramic radiographs. This approach addresses challenges such as anatomical variations and overlapping structures that have historically hindered segmentation performance. The framework combines a ResNet-18 encoder for augmented inputs and a customized CNN encoder for original inputs, allowing for improved feature extraction.

A novel knowledge distillation framework has been proposed to address shortcut learning in medical image analysis, particularly in deep learning models that may rely on irrelevant features. This framework utilizes a teacher network fine-tuned on relevant data to guide a student network trained on a larger, biased dataset, aiming to enhance the robustness of predictions in high-stakes medical applications.

A new domain adaptation pipeline has been developed to enhance the accuracy of galaxy observations by training on simulated TNG50 galaxies and evaluating on real SDSS galaxies. This approach addresses the challenges posed by domain shifts in various factors such as PSF and noise, which can hinder the reliable inference of physical properties like morphology and stellar mass.

A new self-supervised learning framework called CurvSSL has been introduced, which incorporates curvature regularization to enhance the learning process by considering the local geometry of data manifolds. This method builds on existing architectures like Barlow Twins and employs a two-view encoder-projector setup, aiming to improve representation learning in machine learning models.

A recent study has introduced a weakly supervised deep learning framework for pneumonia classification and localization from chest X-ray images, utilizing Gradient-weighted Class Activation Mapping (Grad-CAM) to generate heatmaps that highlight affected regions without the need for costly pixel-level annotations. The framework achieved high accuracy rates of 96-98% across various pre-trained models, including ResNet-18 and EfficientNet-B0.

A new framework called Step-E has been introduced to enhance the training of deep neural networks by addressing the challenges posed by noisy labels and outliers in data. This framework integrates sample selection and model learning into a single optimization process, allowing for a more effective training approach that adapts to the noise patterns present in the data. In tests on the CIFAR-100N dataset, Step-E significantly improved the accuracy of a ResNet-18 model from 43.3% to 50.4%.