Related papers: Diffusion Decoding for Peptide De Novo Sequencing

Semantic segmentation is pixel-wise classification which retains critical spatial information. The "feature map reuse" has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later…

The ability to reconstruct fine-grained network session data, including individual packets, from coarse-grained feature vectors is crucial for improving network security models. However, the large-scale collection and storage of raw network…

Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consist of encoders which decrease spatial resolution while…

Deep convolutional neural networks (DCNN) have recently shown promising results in low-level computer vision problems such as optical flow and disparity estimation, but still, have much room to further improve their performance. In this…

As the global need for large-scale data storage is rising exponentially, existing storage technologies are approaching their theoretical and functional limits in terms of density and energy consumption, making DNA based storage a potential…

Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where…

In this paper, we propose a new self-supervised method, which is called Denoising Masked AutoEncoders (DMAE), for learning certified robust classifiers of images. In DMAE, we corrupt each image by adding Gaussian noises to each pixel value…

The reliable segmentation of retinal vasculature can provide the means to diagnose and monitor the progression of a variety of diseases affecting the blood vessel network, including diabetes and hypertension. We leverage the power of…

In sequence-to-sequence Transformer ASR, autoregressive (AR) models achieve strong accuracy but suffer from slow decoding, while non-autoregressive (NAR) models enable parallel decoding at the cost of degraded performance. We propose a…

Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples…

Deep learning-based joint source-channel coding (deep JSCC) has been demonstrated to be an effective approach for wireless image transmission. Nevertheless, most existing work adopts an autoencoder framework to optimize conventional…

Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…

As in many other scientific domains, we face a fundamental problem when using machine learning to identify proteins from mass spectrometry data: large ground truth datasets mapping inputs to correct outputs are extremely difficult to…

As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep…

Training deep neural networks for 3D segmentation tasks can be challenging, often requiring efficient and effective strategies to improve model performance. In this study, we introduce a novel approach, DeCode, that utilizes label-derived…

Domain Adaptation(DA) for dense prediction tasks is an important topic, which enhances the dense prediction model's performance when tested on its unseen domain. Recently, with the development of Diffusion-based Dense Prediction (DDP)…

To have a superior generalization, a deep learning neural network often involves a large size of training sample. With increase of hidden layers in order to increase learning ability, neural network has potential degradation in accuracy.…

Reducing scan times, radiation dose, and enhancing image quality for lower-performance scanners, are critical in low-dose PET imaging. Deep learning techniques have been investigated for PET image denoising. However, existing models have…

This paper explores the integration of Diophantine equations into neural network (NN) architectures to improve model interpretability, stability, and efficiency. By encoding and decoding neural network parameters as integer solutions to…

While deep learning offers powerful capabilities for scientific research, its application is often hindered by a lack of quantitative reliability. To address this, we introduce a probabilistic denoising framework that simultaneously…