Related papers: DELST: Dual Entailment Learning for Hyperbolic Ima…
Hyperspectral images (HSIs) often suffer from noise arising from both intra-imaging mechanisms and environmental factors. Leveraging domain knowledge specific to HSIs, such as global spectral correlation (GSC) and non-local spatial…
Brain magnetic resonance imaging (MRI) has been extensively employed across clinical and research fields, but often exhibits sensitivity to site effects arising from non-biological variations such as differences in field strength and…
Spatial transcriptomics is an emerging technology that aligns histopathology images with spatially resolved gene expression profiling. It holds the potential for understanding many diseases but faces significant bottlenecks such as…
$\textbf{This is the conference version of our paper: Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learner}$. Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale…
Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts. Since the complex hybrid distortions, it is hard to restore the distorted…
Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new…
Deep Neural Networks are powerful tools for understanding complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. Saliency-Guided Training (SGT) methods try to…
Recently, deep neural networks have greatly advanced histopathology image segmentation but usually require abundant annotated data. However, due to the gigapixel scale of whole slide images and pathologists' heavy daily workload, obtaining…
Social network stores and disseminates a tremendous amount of user shared images. Deep hashing is an efficient indexing technique to support large-scale social image retrieval, due to its deep representation capability, fast retrieval speed…
The growing demands on GPU memory posed by the increasing number of neural network parameters call for training approaches that are more memory-efficient. Previous memory reduction training techniques, such as Low-Rank Adaptation (LoRA) and…
In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…
Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. This study builds upon the previously established two-stage patch-level, multi-label classification method for…
Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning. Classical INRs optimize an entire network from scratch for each subject, leading to inefficient…
Multi-modal large language models (MLLMs) have emerged as a transformative approach for aligning visual and textual understanding. They typically require extremely high computational resources (e.g., thousands of GPUs) for training to…
The self-supervised ultrasound (US) video model pretraining can use a small amount of labeled data to achieve one of the most promising results on US diagnosis. However, it does not take full advantage of multi-level knowledge for learning…
Deformable image registration is able to achieve fast and accurate alignment between a pair of images and thus plays an important role in many medical image studies. The current deep learning (DL)-based image registration approaches…
Surgical instrument segmentation under Federated Learning (FL) is a promising direction, which enables multiple surgical sites to collaboratively train the model without centralizing datasets. However, there exist very limited FL works in…
Learning the hierarchical structure of data in vision-language models is a significant challenge. Previous works have attempted to address this challenge by employing entailment learning. However, these approaches fail to model the…
Self-supervised representation learning has been highly promising for histopathology image analysis with numerous approaches leveraging their patient-slide-patch hierarchy to learn better representations. In this paper, we explore how the…
We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…