Photon counting spectral CT (PCCT) can produce reconstructed attenuation maps in different energy channels, reflecting energy properties of the scanned object. Due to the limited photon numbers and the non-ideal detector response of each energy channel, the reconstructed images usually contain much noise. With the development of Deep Learning (DL) technique, different kinds of DL-based models have been proposed for noise reduction. However, most of the models require clean data set as the training labels, which are not always available in medical imaging field. Inspiring by the similarities of each channel's reconstructed image, we proposed a self-supervised learning based PCCT image enhancement framework via multi-spectral channels (S2MS). In S2MS framework, both the input and output labels are noisy images. Specifically, one single channel image was used as output while images of other single channels and channel-sum image were used as input to train the network, which can fully use the spectral data information without extra cost. The simulation results based on the AAPM Low-dose CT Challenge database showed that the proposed S2MS model can suppress the noise and preserve details more effectively in comparison with the traditional DL models, which has potential to improve the image quality of PCCT in clinical applications.
A self-supervised adaptive low-light video enhancement method, called SALVE, is proposed in this work. SALVE first enhances a few key frames of an input low-light video using a retinex-based low-light image enhancement technique. For each keyframe, it learns a mapping from low-light image patches to enhanced ones via ridge regression. These mappings are then used to enhance the remaining frames in the low-light video. The combination of traditional retinex-based image enhancement and learning-based ridge regression leads to a robust, adaptive and computationally inexpensive solution to enhance…
A Generic Fundus Image Enhancement Network Boosted by Frequency Self-supervised Representation Learning
Southern University of Science and Technology（南方科技大学）；Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究所）；South China University of Technology（华南理工大学）；Pazhou Lab（琶洲实验室）；New York University（纽约大学）；Beijing Information Science and Technology University（北京信息科技大学）
This paper proposes a self-supervised low light image enhancement method based on deep learning. Inspired by information entropy theory and Retinex model, we proposed a maximum entropy based Retinex model. With this model, a very simple network can separate the illumination and reflectance, and the network can be trained with low light images only. We introduce a constraint that the maximum channel of the reflectance conforms to the maximum channel of the low light image and its entropy should be largest in our model to achieve self-supervised learning. Our model is very simple and does not re…
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms. In this paper, we propose a self-supervised low-light image enhancement framework (SID-NISM), which consists of two components, a Self-supervised Image Decomposition Network (SID-Net) and a Nonlinear Illumination Saturation Mapping function (NISM). As a self-supervised network, SID-Net could decompose the given low-light image into its reflectance, illumination …
This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to cleaning recordings of a test-time speaker is limited to a few seconds, but noisy recordings of the speaker are abundant. We develop a simple contrastive learning procedure which treats the abundant noisy data as makeshift training targets through pairwise noise injection: the model is pretrained to maximize agreement between pairs of differently deformed iden…
Reducing the interference noise in a monaural noisy speech signal has been a challenging task for many years. Compared to traditional unsupervised speech enhancement methods, e.g., Wiener filtering, supervised approaches, such as algorithms based on hidden Markov models (HMM), lead to higher-quality enhanced speech signals. However, the main practical difficulty of these approaches is that for each noise type a model is required to be trained a priori. In this paper, we investigate a new class of supervised speech denoising algorithms using nonnegative matrix factorization (NMF). We propose a …
A Two-Stage Multi-Scale Attention-Based Network for Weakly Supervised Cataract Fundus Image Enhancement
Hunan Institute of Technology（湖南工学院）；National and Local Joint Engineering Laboratory of Computer Aided Design（计算机辅助设计国家地方联合工程实验室）；Dalian University of Technology（大连理工大学）
Low light conditions in aerial images adversely affect the performance of several vision based applications. There is a need for methods that can efficiently remove the low light attributes and assist in the performance of key vision tasks. In this work, we propose a new method that is capable of enhancing the low light image in a self-supervised fashion, and sequentially apply detection and segmentation tasks in an end-to-end manner. The proposed method occupies a very small overhead in terms of memory and computational power over the original algorithm and delivers superior results. Addition…
This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their enhancement function towards a particular speaker's voice, expecting to solve a narrower problem. Hence, specialists are capable of achieving more optimal performance in addition to reducing computational complexity. However, naive personalization methods can require clean speech from the target user, which is inconvenient to acquire, e.g., due to subpar recordin…
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the test-time user, a personalized speech enhancement model can be trained using self-supervised learning. One straightforward approach to model personalization is to use the target speaker's noisy recordings as pseudo-sources. Then, a pseudo denoising model learns to remove injected training noises and recover the pseudo-sources. However, this approach is volatile …
This paper proposes a self-supervised low light image enhancement method based on deep learning, which can improve the image contrast and reduce noise at the same time to avoid the blur caused by pre-/post-denoising. The method contains two deep sub-networks, an Image Contrast Enhancement Network (ICE-Net) and a Re-Enhancement and Denoising Network (RED-Net). The ICE-Net takes the low light image as input and produces a contrast enhanced image. The RED-Net takes the result of ICE-Net and the low light image as input, and can re-enhance the low light image and denoise at the same time. Both of …
Bose Corporation（博士公司）；Georgia Institute of Technology（佐治亚理工学院）
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative speech synthesis, where the system's output is synthesized by a neural vocoder after an inherently lossy feature-denoising step. In this paper, we propose a denoising vocoder (DeVo) approach, where a vocoder accepts noisy representations and learns to directly synthesize clean speech. We leverage rich representations from self-supervised learning (SSL) speech mod…
Semi-LLIE: Semi-supervised Contrastive Learning with Mamba-based Low-light Image Enhancement
Northwestern Polytechnical University（西北工业大学）；Science and Technology on Electromechanical Dynamic Control Laboratory（机电动态控制重点实验室）；Key Laboratory of Intelligent Interaction and Applications (Northwestern Polytechnical University), Ministry of Industry and Information Technology（工业和信息化部智能交互与应用重点实验室（西北工业大学））
Recently, deep learning approaches have become the main research frontier for biological image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times. However, due to the difficulty of obtaining matched reference data for supervised learning, there has been increasing interest in unsupervised learning approaches that do not need paired reference data. In particular, self-supervised learning and generative models have been successfully used for various biological imaging applications. In this paper, we overview these approaches from…
A Frequency-Aware Self-Supervised Learning for Ultra-Wide-Field Image Enhancement
College of Information Engineering, Zhejiang University of Technology, Hangzhou, China（浙江工业大学信息工程学院）；Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China（中国科学院宁波材料技术与工程研究所）；Department of Eye and Vision Science, University of Liverpool, Liverpool, UK（利物浦大学眼科学与视觉科学系）；School of Biomedical Engineering, ShanghaiTech University, Shanghai, China（上海科技大学生物医学工程学院）
CUHK-Sensetime Joint Laboratory, The Chinese University of Hong Kong（香港中文大学-商汤联合实验室，香港中文大学）
We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement. Traditional image enhancement frameworks typically involve training models in a fully-supervised manner, which require expensive annotations in the form of aligned image pairs. In contrast to these approaches, our proposed EnhanceGAN only requires weak supervision (binary labels on image aesthetic quality) and is able to learn enhancement operators for the task of aesthetic-based image enhancement. In particular, we show the effectiveness of a piecewise color enhancement module trained with …
LMT-GP: Combined Latent Mean-Teacher and Gaussian Process for Semi-supervised Low-light Image Enhancement
School of Computer and Information, Hefei University of Technology（合肥工业大学计算机与信息学院）；Department of Automation, University of Science and Technology of China（中国科学技术大学自动化系）
Low light images suffer from severe noise, low brightness, low contrast, etc. In previous researches, many image enhancement methods have been proposed, but few methods can deal with these problems simultaneously. In this paper, to solve these problems simultaneously, we propose a low light image enhancement method that can combined with supervised learning and previous HSV (Hue, Saturation, Value) or Retinex model based image enhancement methods. First, we analyse the relationship between the HSV color space and the Retinex theory, and show that the V channel (V channel in HSV color space, eq…
Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography
School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）；Nanyang Technological University（南洋理工大学）；Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE, Nanjing University（南京大学极端性能光电器件与系统教育部重点实验室）
A Semi-supervised Physics-Aware Triple-Stream Underwater Image Enhancement Network
State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China（物理海洋学国家重点实验室和中国海洋大学信息科学与工程学院）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen university（中山大学深圳校区计算机科学与技术学院）；Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology（深圳视觉目标检测与识别重点实验室，哈尔滨工业大学）
NTT Software Innovation Center（NTT软件创新中心）；NTT Media Intelligence Laboratories（NTT媒体智能实验室）
The rotation prediction (Rotation) is a simple pretext-task for self-supervised learning (SSL), where models learn useful representations for target vision tasks by solving pretext-tasks. Although Rotation captures information of object shapes, it hardly captures information of textures. To tackle this problem, we introduce a novel pretext-task called image enhanced rotation prediction (IE-Rot) for SSL. IE-Rot simultaneously solves Rotation and another pretext-task based on image enhancement (e.g., sharpening and solarizing) while maintaining simplicity. Through the simultaneous prediction of …
Blind Ultrasound Image Enhancement via Self-Supervised Physics-Guided Degradation Modeling
Department of Computer Engineering, College of Computing and Mathematics, King Fahd University of Petroleum & Minerals (KFUPM)（计算机工程系，计算与数学学院，国王法赫德石油与矿物大学）；SDAIA–KFUPM Joint Research Center for Artificial Intelligence (JRC-AI), King Fahd University of Petroleum & Minerals（人工智能联合研究中心（JRC-AI），国王法赫德石油与矿物大学）；Department of Computer Science and Information Technology, Sir Syed University of Engineering and Technology (SSUET)（计算机科学与信息科技系，西德大学工程与技术学院）；Digital Technology & Innovation Center, Siemens Healthineers, Princeton, NJ 08540, USA（数字技术与创新中心，西门子健康部，美国新泽西州普林斯顿）；Department of Aerospace Engineering, King Fahd University of Petroleum & Minerals (KFUPM)（航空航天工程系，国王法赫德石油与矿物大学）；Interdisciplinary Research Center for Smart Mobility and Logistics, King Fahd University of Petroleum & Minerals (KFUPM)（智能交通与物流跨学科研究中心，国王法赫德石油与矿物大学）
Hebrew University of Jerusalem（希伯来大学）；Meta AI Research（Meta人工智能研究院）
Speech enhancement has seen great improvement in recent years using end-to-end neural networks. However, most models are agnostic to the spoken phonetic content. Recently, several studies suggested phonetic-aware speech enhancement, mostly using perceptual supervision. Yet, injecting phonetic features during model optimization can take additional forms (e.g., model conditioning). In this paper, we conduct a systematic comparison between different methods of incorporating phonetic information in a speech enhancement model. By conducting a series of controlled experiments, we observe the influen…
Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. Although SSL has recently reached a milestone: outperforming supervised methods in many modalities\dots the theoretical foundations are limited, method-specific, and fail to provide principled design guidelines to practitioners. In this paper, we propose a unifying framework under the helm of spectral manifold learning to address those limitations. Through the course of this study, we will rigorously demonstrate that VICReg, SimCLR, BarlowTwins et al. correspo…
Carnegie Mellon University（卡内基梅隆大学）；University of Pittsburgh（匹兹堡大学）
Vessel segmentation is an essential task in many clinical applications. Although supervised methods have achieved state-of-art performance, acquiring expert annotation is laborious and mostly limited for two-dimensional datasets with a small sample size. On the contrary, unsupervised methods rely on handcrafted features to detect tube-like structures such as vessels. However, those methods require complex pipelines involving several hyper-parameters and design choices rendering the procedure sensitive, dataset-specific, and not generalizable. We propose a self-supervised method with a limited …
Institute of Microelectronics of Chinese Academy of Sciences（中国科学院微电子研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Retinal vessel segmentation based on deep learning requires a lot of manual labeled data. That is time-consuming, laborious and professional. What is worse, the acquisition of abundant fundus images is difficult. These problems are more serious due to the presence of abnormalities, varying size and shape of the vessels, non-uniform illumination and anatomical changes. In this paper, we propose a data-efficient semi-supervised learning framework, which effectively combines the existing deep learning network with GAN and self-training ideas. In view of the difficulty of tuning hyper-parameters o…
Self-Supervised Enhancement of Forward-Looking Sonar Images: Bridging Cross-Modal Degradation Gaps through Feature Space Transformation and Multi-Frame Fusion
College of Electronic Engineering, Naval University of Engineering（电子工程学院，海军工程大学）；College of Meteorology and Oceanography, National University of Defense Technology（气象海洋学院，国防科技大学）；College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学）；Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）
Coded aperture snapshot spectral imaging (CASSI) makes it possible to recover 3D hyperspectral data from a single 2D image. However, the reconstruction problem is severely underdetermined and efforts to improve the compression ratio typically make the imaging system more complex and cause a significant loss of incoming light intensity. In this paper, we propose a novel approach to CASSI which enables capturing both spectrally sheared and integrated image of a scene with a single camera. We performed hyperspectral imaging of three different testing scenes in the spectral range of 500-900 nm. We…
