Related papers: FATE: Feature-Agnostic Transformer-based Encoder f…

The heterogeneous network is a robust data abstraction that can model entities of different types interacting in various ways. Such heterogeneity brings rich semantic information but presents nontrivial challenges in aggregating the…

Human cancers present a significant public health challenge and require the discovery of novel drugs through translational research. Transcriptomics profiling data that describes molecular activities in tumors and cancer cell lines are…

Image attribute transfer aims to change an input image to a target one with expected attributes, which has received significant attention in recent years. However, most of the existing methods lack the ability to de-correlate the target…

The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. To apply transformers across different data modalities,…

Surgical scene segmentation is a fundamental task for robotic-assisted laparoscopic surgery understanding. It often contains various anatomical structures and surgical instruments, where similar local textures and fine-grained structures…

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence…

Accurate segmentation of organs and lesions in medical images is essential for clinical applications including diagnosis, prognosis, and treatment planning. While Vision Transformers (ViTs) have shown impressive segmentation performance,…

The high-dimensional nature of the 4-D light field (LF) poses great challenges in achieving efficient and effective feature embedding, that severely impacts the performance of downstream tasks. To tackle this crucial issue, in contrast to…

The computer-aided detection (CADe) systems are developed to assist pathologists in slide assessment, increasing diagnosis efficiency and reducing missing inspections. Many studies have shown such a CADe system with deep learning approaches…

Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability stemming from two factors: 1) limited annotated image-event-depth datasets causing insufficient…

Test-Time Adaptation (TTA) aims to enhance the generalization of deep learning models when faced with test data that exhibits distribution shifts from the training data. In this context, only a pre-trained model and unlabeled test data are…

Pre-trained foundation models have demonstrated remarkable success in audio, vision and language, yet their potential for general machine signal modeling with arbitrary sampling rates-covering acoustic, vibration, and other industrial…

Attributed graph embedding, which learns vector representations from graph topology and node features, is a challenging task for graph analysis. Recently, methods based on graph convolutional networks (GCNs) have made great progress on this…

Most existing visual search systems are deployed based upon fixed kinds of visual features, which prohibits the feature reusing across different systems or when upgrading systems with a new type of feature. Such a setting is obviously…

One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this challenge by either…

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance…

By implementing machine learning at the network edge, edge learning trains models by leveraging rich data distributed at edge devices (e.g., smartphones and sensors) and in return endow on them capabilities of seeing, listening, and…

This work introduced a novel GAN architecture for unsupervised image translation on the task of face style transform. A spectral attention-based mechanism is embedded into the design along with spatial attention on the image contents. We…

Synthesizing high-quality dynamic medical videos remains a significant challenge due to the need for modeling both spatial consistency and temporal dynamics. Existing Transformer-based approaches face critical limitations, including…

Training deep learning models on limited data while maintaining generalization is one of the fundamental challenges in molecular property prediction. One effective solution is transferring knowledge extracted from abundant datasets to those…