Related papers: Fractional Denoising for 3D Molecular Pre-training

In this paper, we present a deep learning model that exploits the power of self-supervision to perform 3D point cloud completion, estimating the missing part and a context region around it. Local and global information are encoded in a…

In low-visibility marine environments characterized by turbidity and darkness, acoustic cameras serve as visual sensors capable of generating high-resolution 2D sonar images. However, acoustic camera images are interfered with by complex…

The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature…

Pretraining with large-scale 3D volumes has a potential for improving the segmentation performance on a target medical image dataset where the training images and annotations are limited. Due to the high cost of acquiring pixel-level…

Astronomical imaging remains noise-limited under practical observing conditions. Standard calibration pipelines remove structured artifacts but largely leave stochastic noise unresolved. Although learning-based denoising has shown strong…

The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and…

Coarse-grained models have proven helpful for simulating complex systems over long timescales to provide molecular insights into various processes. Methodologies for systematic parameterization of the underlying energy function, or force…

The field of image denoising is currently dominated by discriminative deep learning methods that are trained on pairs of noisy input and clean target images. Recently it has been shown that such methods can also be trained without clean…

This paper presents DFR (Decompose, Fuse and Reconstruct), a novel framework that addresses the fundamental challenge of effectively utilizing multi-modal guidance in few-shot segmentation (FSS). While existing approaches primarily rely on…

Machine-learning models have recently encountered enormous success for predicting the properties of materials. These are often trained based on data that present various levels of accuracy, with typically much less high- than low-fidelity…

Is it possible to recover an image from its noisy version using convolutional neural networks? This is an interesting problem as convolutional layers are generally used as feature detectors for tasks like classification, segmentation and…

Object detection models demand large-scale annotated datasets, which are costly and labor-intensive to create. This motivated Imaginary Supervised Object Detection (ISOD), where models train on synthetic images and test on real images.…

Convolutional neural networks (CNNs) have shown outstanding performance on image denoising with the help of large-scale datasets. Earlier methods naively trained a single CNN with many pairs of clean-noisy images. However, the conditional…

Adversarial Robustness Distillation (ARD) is a novel method to boost the robustness of small models. Unlike general adversarial training, its robust knowledge transfer can be less easily restricted by the model capacity. However, the…

Decoding visual stimuli from neural responses recorded by functional Magnetic Resonance Imaging (fMRI) presents an intriguing intersection between cognitive neuroscience and machine learning, promising advancements in understanding human…

Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series,…

In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of latent denoising diffusion models, when used in combination…

3D decomposition/segmentation still remains a challenge as large-scale 3D annotated data is not readily available. Contemporary approaches typically leverage 2D machine-generated segments, integrating them for 3D consistency. While the…

Image demosaicking and denoising are the two key fundamental steps in digital camera pipelines, aiming to reconstruct clean color images from noisy luminance readings. In this paper, we propose and study Wild-JDD, a novel learning framework…

Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to…