相关论文: Training-Free Model Ensemble for Single-Image Supe…

Existing beamforming-based full-duplex solutions for multi-antenna wireless systems often rely on explicit estimation of the self-interference channel. The pilot overhead of such estimation, however, can be prohibitively high in…

Neural network ensembles have been effectively used to improve generalization by combining the predictions of multiple independently trained models. However, the growing scale and complexity of deep neural networks have led to these methods…

Recent ensemble learning methods for image classification have been shown to improve classification accuracy with low extra cost. However, they still require multiple trained models for ensemble inference, which eventually becomes a…

For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring…

Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this…

Recently, single gray/RGB image super-resolution reconstruction task has been extensively studied and made significant progress by leveraging the advanced machine learning techniques based on deep convolutional neural networks (DCNNs).…

Image reconstruction from undersampled k-space data plays an important role in accelerating the acquisition of MR data, and a lot of deep learning-based methods have been exploited recently. Despite the achieved inspiring results, the…

Neural operators are promising surrogates for dynamical systems but when trained with standard L2 losses they tend to oversmooth fine-scale turbulent structures. Here, we show that combining operator learning with generative modeling…

Recently, machine learning based single image super resolution (SR) approaches focus on jointly learning representations for high-resolution (HR) and low-resolution (LR) image patch pairs to improve the quality of the super-resolved images.…

The volume estimation of brain regions from MRI data is a key problem in many clinical applications, where the acquisition of data at high spatial resolution is desirable. While parallel MRI and constrained image reconstruction algorithms…

Deep ensemble is a simple yet powerful way to improve the performance of deep neural networks. Under this motivation, recent works on mode connectivity have shown that parameters of ensembles are connected by low-loss subspaces, and one can…

The deep convolutional neural networks have achieved significant improvements in accuracy and speed for single image super-resolution. However, as the depth of network grows, the information flow is weakened and the training becomes harder…

There is a growing necessity for edge training to adapt to dynamically changing environment. Neuromorphic computing represents a significant pathway for high-efficiency intelligent computation in energy-constrained edges, but existing…

Composed Image Retrieval (CIR) presents a significant challenge as it requires jointly understanding a reference image and a modified textual instruction to find relevant target images. Some existing methods attempt to use a two-stage…

Machine learning (ML) continues to grow in importance across nearly all domains and is a natural tool in modeling to learn from data. Often a tradeoff exists between a model's ability to minimize bias and variance. In this paper, we utilize…

We introduce SEE&TREK, the first training-free prompting framework tailored to enhance the spatial understanding of Multimodal Large Language Models (MLLMS) under vision-only constraints. While prior efforts have incorporated modalities…

Deep learning has achieved state-of-the-art accuracies on several computer vision tasks. However, the computational and energy requirements associated with training such deep neural networks can be quite high. In this paper, we propose a…

The core problem of Magnetic Resonance Imaging (MRI) is the trade off between acceleration and image quality. Image reconstruction and super-resolution are two crucial techniques in Magnetic Resonance Imaging (MRI). Current methods are…

Model merging combines independently trained models into a single multi-task model. However, most existing approaches focus primarily on avoiding task interference. We argue that its greater potential lies in enabling task synergy, where…

Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…