相关论文: SpectralX: Parameter-efficient Domain Generalizati…

Convolutional Neural Networks have been the backbone of recent rapid progress in Single-Image Super-Resolution. However, existing networks are very deep with many network parameters, thus having a large memory footprint and being…

Semantic segmentation relying solely on RGB data often struggles in challenging conditions such as low illumination and obscured views, limiting its reliability in critical applications like autonomous driving. To address this, integrating…

Modern multispectral feature fusion for object detection faces two critical limitations: (1) Excessive preference for local complementary features over cross-modal shared semantics adversely affects generalization performance; and (2) The…

Semantic segmentation is a critical step in automated image interpretation and analysis where pixels are classified into one or more predefined semantically meaningful classes. Deep learning approaches for semantic segmentation rely on…

Recent advances in pre-trained language models (PLMs) have demonstrated their capabilities in capturing universal knowledge, making them promising for radar signal processing applications. Nevertheless, directly fine-tuning PLMs on radar…

Modern Foundation Models (FMs) are typically trained on corpora spanning a wide range of different data modalities, topics and downstream tasks. Utilizing these models can be very computationally expensive and is out of reach for most…

Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most…

Training large, general-purpose language models poses significant challenges. The growing availability of specialized expert models, fine-tuned from pretrained models for specific tasks or domains, offers a promising alternative. Leveraging…

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their performance drops significantly under domain (covariate) shift, a…

High spatial frequency information, including fine details like textures, significantly contributes to the accuracy of semantic segmentation. However, according to the Nyquist-Shannon Sampling Theorem, high-frequency components are…

Recent advances in autonomous driving have underscored the importance of accurate 3D object detection, with LiDAR playing a central role due to its robustness under diverse visibility conditions. However, different vehicle platforms often…

Adapting pretrained language models to novel domains, such as clinical applications, traditionally involves retraining their entire set of parameters. Parameter-Efficient Fine-Tuning (PEFT) techniques for fine-tuning language models…

Recent studies show that the visual place recognition (VPR) method using pre-trained visual foundation models can achieve promising performance. In our previous work, we propose a novel method to realize seamless adaptation of foundation…

Parameter-efficient fine-tuning (PEFT) techniques such as low-rank adaptation (LoRA) can effectively adapt large pre-trained foundation models to downstream tasks using only a small fraction (0.1%-10%) of the original trainable weights. An…

X-ray speckles have been used for a wide variety of experiments, ranging from imaging (and tomography), wavefront sensing, spatial coherence measurements all the way to x-ray photon correlation spectroscopy (XPCS) and ptychography. In the…

Feature selection of high-dimensional labeled data with limited observations is critical for making powerful predictive modeling accessible, scalable, and interpretable for domain experts. Spectroscopy data, which records the interaction…

We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing…

Adapting pre-trained foundation models for various downstream tasks has been prevalent in artificial intelligence. Due to the vast number of tasks and high costs, adjusting all parameters becomes unfeasible. To mitigate this, several…

The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain…