Related papers: MVKTrans: Multi-View Knowledge Transfer for Robust…

Biosignals offer valuable insights into the physiological states of the human body. Although biosignal modalities differ in functionality, signal fidelity, sensor comfort, and cost, they are often intercorrelated, reflecting the holistic…

Deploying deep learning models on resource-constrained edge devices remains a major challenge in smart agriculture due to the trade-off between computational efficiency and recognition accuracy. To address this challenge, this study…

Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges in Knowledge Distillation (KD) are: 1) balancing learning…

Medical vision-language pretraining (VLP) models have recently been investigated for their generalization to diverse downstream tasks. However, current medical VLP methods typically force the model to learn simple and complex concepts…

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good"…

Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…

In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing knowledge transfer methods (e.g., backbone sharing, knowledge distillation) often hinge on shared…

Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing…

The increase in high-dimensional multiomics data demands advanced integration models to capture the complexity of human diseases. Graph-based deep learning integration models, despite their promise, struggle with small patient cohorts and…

Multi-view learning often faces challenges in effectively leveraging images captured from different angles and locations. This challenge is particularly pronounced when addressing inconsistencies and uncertainties between views. In this…

Multimodal ophthalmic imaging-based diagnosis integrates color fundus image with optical coherence tomography (OCT) to provide a comprehensive view of ocular pathologies. However, the uneven global distribution of healthcare resources often…

Single-cell multi-omics data contain huge information of cellular states, and analyzing these data can reveal valuable insights into cellular heterogeneity, diseases, and biological processes. However, as cell differentiation \& development…

In mixed domain semi-supervised medical image segmentation (MiDSS), achieving superior performance under domain shift and limited annotations is challenging. This scenario presents two primary issues: (1) distributional differences between…

The lack of well-annotated datasets in computational pathology (CPath) obstructs the application of deep learning techniques for classifying medical images. %Since pathologist time is expensive, dataset curation is intrinsically difficult.…

Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly…

Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities such as images and genetic information. We investigate whether…

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input…

Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significant appearance differences between modalities make this task…

Human expertise in chemistry and biomedicine relies on contextual molecular understanding, a capability that large language models (LLMs) can extend through fine-grained alignment between molecular structures and text. Recent multimodal…

Histo-genomic multimodal survival prediction has garnered growing attention for its remarkable model performance and potential contributions to precision medicine. However, a significant challenge in clinical practice arises when only…