Uniform Selection And Representation Matching: A Framework For Classifying Wound Healing Stage.

We propose the Uniform Selection and Representation Matching framework, an image classification framework that leverages co-teaching, contrastive learning, representation matching, and uniform selection to perform accurate wound stage classification with limited and noisy-labeled data. Given that descriptors of wound stages are under-specified, making accurate recognition difficult, images that generate low classification confidence are identified using an entropy-based selection process. Pseudo-labels are assigned to the low-confidence images through the representation matching process, where images are embedded into latent space and labels are assigned through majority voting.

Toward metacognition: subject-aware contrastive deep fusion representation learning for EEG analysis.

We propose a subject-aware contrastive learning deep fusion neural network framework for effectively classifying subjects' confidence levels in the perception of visual stimuli. The framework, called WaveFusion, is composed of lightweight convolutional neural networks for per-lead time-frequency analysis and an attention network for integrating the lightweight modalities for final prediction. To facilitate the training of WaveFusion, we incorporate a subject-aware contrastive learning approach by taking advantage of the heterogeneity within a multi-subject electroencephalogram dataset to boost representation learning and classification accuracy.

WaveFusion Squeeze-and-Excitation: Towards an Accurate and Explainable Deep Learning Framework in Neuroscience.

We introduce WaveFusion Squeeze-and-Excite, a multi-modal deep fusion architecture, as a practical and effective framework for classifying and localizing neurological events. WaveFusion SE is composed of lightweight CNNs for per-lead time-frequency analysis and an attention network called squeeze and excitation network with a temperature factor for effectively integrating lightweight modalities for final prediction. Our proposed architecture demonstrates high accuracy in classifying subjects' anxiety levels with an overall accuracy of 97.