Related papers: Patch Rebirth: Toward Fast and Transferable Model …

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…

Traditional model-based image reconstruction (MBIR) methods combine forward and noise models with simple object priors. Recent application of deep learning methods for image reconstruction provides a successful data-driven approach to…

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Programs offer compactness and structure that makes them an attractive representation for visual data. We explore how code rewriting can be used to improve systems for inferring programs from visual data. We first propose Sparse…

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…

Image restoration has witnessed significant advancements with the development of deep learning models. Transformer-based models, particularly those using window-based self-attention, have become a dominant force. However, their performance…

Vision Transformers (ViTs) have achieved remarkable success in various computer vision tasks. However, ViTs have a huge computational cost due to their inherent reliance on multi-head self-attention (MHSA), prompting efforts to accelerate…

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with varying sizes. While Convolutional Neural Networks (CNNs) have…

Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment.…

Magnetic resonance imaging (MRI) is known to be a slow imaging modality and undersampling in k-space has been used to increase the imaging speed. However, image reconstruction from undersampled k-space data is an ill-posed inverse problem.…

Diffusion models show promising generation capability for a variety of data. Despite their high generation quality, the inference for diffusion models is still time-consuming due to the numerous sampling iterations required. To accelerate…

Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch of this task divides the pavement image into patches and…

In image editing employing diffusion models, it is crucial to preserve the reconstruction fidelity to the original image while changing its style. Although existing methods ensure reconstruction fidelity through optimization, a drawback of…

Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce training cost, yet na\"ive…

Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different…

Full-waveform inversion (FWI) is a powerful geophysical imaging technique that infers high-resolution subsurface physical parameters by solving a non-convex optimization problem. However, due to limitations in observation, e.g., limited…

Generative diffusion models are becoming one of the most popular prior in image restoration (IR) tasks due to their remarkable ability to generate realistic natural images. Despite achieving satisfactory results, IR methods based on…

Diffusion models are a powerful class of generative models that iteratively denoise samples to produce data. While many works have focused on the number of iterations in this sampling procedure, few have focused on the cost of each…