Related papers: Adaptive Query Prompting for Multi-Domain Landmark…

Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific…

The accurate segmentation of medical images is a crucial step in obtaining reliable morphological statistics. However, training a deep neural network for this task requires a large amount of labeled data to ensure high-accuracy results. To…

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Recent work explored the capabilities of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA) through few-shot prompting, requiring substantially fewer annotated examples while achieving notable improvements over zero-shot…

Deep Neural Networks (DNNs) have already become a crucial computational approach to revealing the spatial patterns in the human brain; however, there are three major shortcomings in utilizing DNNs to detect the spatial patterns in…

Anomaly detection in medical images is an important yet challenging task due to the diversity of possible anomalies and the practical impossibility of collecting comprehensively annotated data sets. In this work, we tackle unsupervised…

With the widespread success of deep learning in biomedical image segmentation, domain shift becomes a critical and challenging problem, as the gap between two domains can severely affect model performance when deployed to unseen data with…

Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples,…

Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised learning methods require extensive labeled data, which is often scarce in real-world…

Generating high-quality pseudo-labels on the cloud is crucial for cloud-edge object detection, especially in dynamic traffic monitoring where data distributions evolve. Existing methods often assume reliable cloud models, neglecting…

It is critical to deploy complicated neural network models on hardware with limited resources. This paper proposes a novel model quantization method, named the Low-Cost Proxy-Based Adaptive Mixed-Precision Model Quantization (LCPAQ), which…

Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…

Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations,…

Meta-learning facilitates few-shot hyperspectral target detection (HTD), but adapting deep backbones remains challenging. Full-parameter fine-tuning is inefficient and prone to overfitting, and existing methods largely ignore the…

Although current prompt learning methods have successfully been designed to effectively reuse the large pre-trained models without fine-tuning their large number of parameters, they still have limitations to be addressed, i.e., without…

Anomaly detection (AD) plays a vital role across a wide range of domains, but its performance might deteriorate when applied to target domains with limited data. Domain Adaptation (DA) offers a solution by transferring knowledge from a…

Segment Anything Model (SAM), a prompt-driven foundation model for natural image segmentation, has demonstrated impressive zero-shot performance. However, SAM does not work when directly applied to medical image segmentation, since SAM…

Nucleus instance segmentation in histology images is crucial for a broad spectrum of clinical applications. Current dominant algorithms rely on regression of nuclear proxy maps. Distinguishing nucleus instances from the estimated maps…

Soft prompt tuning is a widely studied parameter-efficient fine-tuning method. However, it has a clear drawback: many soft tokens must be inserted into the input sequences to guarantee downstream performance. As a result, soft prompt tuning…

Although the lightweight Vision Transformer has significantly advanced image super-resolution (SR), it faces the inherent challenge of a limited receptive field due to the window-based self-attention modeling. The quadratic computational…