We introduce Corrupted Image Modeling (CIM) for self-supervised visual pre-training. CIM uses an auxiliary generator with a small trainable BEiT to corrupt the input image instead of using artificial [MASK] tokens, where some patches are randomly selected and replaced with plausible alternatives sampled from the BEiT output distribution. Given this corrupted image, an enhancer network learns to either recover all the original image pixels, or predict whether each visual token is replaced by a generator sample or not. The generator and the enhancer are simultaneously trained and synergistically updated. After pre-training, the enhancer can be used as a high-capacity visual encoder for downstream tasks. CIM is a general and flexible visual pre-training framework that is suitable for various network architectures. For the first time, CIM demonstrates that both ViT and CNN can learn rich visual representations using a unified, non-Siamese framework. Experimental results show that our approach achieves compelling results in vision benchmarks, such as ImageNet classification and ADE20K semantic segmentation.
Deep convolutional neural networks (DCNNs) have contributed many breakthroughs in segmentation tasks, especially in the field of medical imaging. However, \textit{domain shift} and \textit{corrupted annotations}, which are two common problems in medical imaging, dramatically degrade the performance of DCNNs in practice. In this paper, we propose a novel robust cross-denoising framework using two peer networks to address domain shift and corrupted label problems with a peer-review strategy. Specifically, each network performs as a mentor, mutually supervised to learn from reliable samples selec…
Nankai University（南开大学）；Xi’an Jiaotong University（西安交通大学）；Inception Institute of Artificial Intelligence (IIAI)（人工智能 inception 研究院）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；Chongqing University（重庆大学）
Supervised deep networks have achieved promisingperformance on image denoising, by learning image priors andnoise statistics on plenty pairs of noisy and clean images. Unsupervised denoising networks are trained with only noisy images. However, for an unseen corrupted image, both supervised andunsupervised networks ignore either its particular image prior, the noise statistics, or both. That is, the networks learned from external images inherently suffer from a domain gap problem: the image priors and noise statistics are very different between the training and test images. This problem become…
Columbia University（哥伦比亚大学）；Imperial College London（帝国理工学院）；The University of Alabama（阿拉巴马大学）
Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance degradation at test time. In this paper, we propose a novel deep learning framework, namely Co-Seg, to collaboratively train segmentation networks on datasets which include low-quality noisy labels. Our approach first trains two networks simultaneously to sift through all samples and obtain a subset with reliable labels. Then, an efficient yet easily-implemented l…
Background: Accurate segmentation of microscopic structures such as bio-artificial capsules in microscopy imaging is a prerequisite to the computer-aided understanding of important biomechanical phenomenons. State-of-the-art segmentation performances are achieved by deep neural networks and related data-driven approaches. Training these networks from only a few annotated examples is challenging while producing manually annotated images that provide supervision is tedious. Method: Recently, self-supervision, i.e. designing a neural pipeline providing synthetic or indirect supervision, has prove…
Nanjing University of Science and Technology（南京理工大学）；Illinois Institute of Technology（伊利诺伊理工学院）
Deep learning-based video inpainting has yielded promising results and gained increasing attention from researchers. Generally, these methods usually assume that the corrupted region masks of each frame are known and easily obtained. However, the annotation of these masks are labor-intensive and expensive, which limits the practical application of current methods. Therefore, we expect to relax this assumption by defining a new semi-supervised inpainting setting, making the networks have the ability of completing the corrupted regions of the whole video using the annotated mask of only one fram…
Deep neural networks have achieved satisfactory performance in piles of medical image analysis tasks. However the training of deep neural network requires a large amount of samples with high-quality annotations. In medical image segmentation, it is very laborious and expensive to acquire precise pixel-level annotations. Aiming at training deep segmentation models on datasets with probably corrupted annotations, we propose a novel Meta Corrupted Pixels Mining (MCPM) method based on a simple meta mask network. Our method is targeted at automatically estimate a weighting map to evaluate the impor…
When pixel-level masks or partial annotations are not available for training neural networks for semantic segmentation, it is possible to use higher-level information in the form of bounding boxes, or image tags. In the imaging sciences, many applications do not have an object-background structure and bounding boxes are not available. Any available annotation typically comes from ground truth or domain experts. A direct way to train without masks is using prior knowledge on the size of objects/classes in the segmentation. We present a new algorithm to include such information via constraints o…
We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the representation of an image R(x), if we are only given a corrupted version A(x), for some known forward operator A. We propose a supervised inversion method that uses a contrastive objective to obtain excellent representations for highly corrupted images. Using a linear probe on our robust representations, we achieve a higher accuracy than end-to-end supervised ba…
We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can thus be applied in situations where such data is unacceptably expensive or impossible to acquire. We build on a recent technique that removes the need for reference data by employing networks with a "blind spot" in the receptive field, and significantly improve two key aspects: image quality and training efficiency. Our result quality is on par with state-of-t…
ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization
organization= School of Software Engineering,Xi'an Jiaotong University , addressline= 28 Xianning West Road , city= Xi'an , postcode= 710049 , state= Shaanxi , country= China
Caltech（加州理工学院）；Google（谷歌）；University of Edinburgh（爱丁堡大学）；Alan Turing Institute（艾伦·图灵研究所）；University of Copenhagen（哥本哈根大学）
Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well understood, the field still lacks widely accepted best practices for replicating this success on other datasets. As a first step in this direction, we study contrastive self-supervised learning on four diverse large-scale datasets. By looking through the lenses of data quantity, data domain, data quality, and task granularity, we provide new insights into the necess…
We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original point cloud without corruption. The encoder learns the high-level latent representations of the points clouds in a low-dimensional subspace and recovers the original structure. In this work, we have used Transformers and PointNet-based Autoencoders. The proposed framework also addresses some of the limitations of Transformers-based Masked Autoencoders which are prone to leakage o…
An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however, breaks this paradigm and enables adaption at test-time. We combine meta-learning, self-supervision and test-time training to learn to adapt to unseen test distributions. By minimizing the self-supervised loss, we learn task-specific model parameters for different tasks. A meta-model is optimized such that its adaption to the different task-specific models le…
Explicit Abnormality Extraction for Unsupervised Motion Artifact Reduction in Magnetic Resonance Imaging
School of Electrical Engineering and Automation, Wuhan University（武汉大学电气与自动化学院）；University Hospital Heidelberg（海德堡大学医院）；Vitalent Consulting（维塔伦特咨询公司）；College of Science and Engineering, James Cook University（詹姆斯库克大学科学与工程学院）；Uppsala University（乌普萨拉大学）；School of Computer Science, University of Sydney（悉尼大学计算机学院）
Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
South China University of Technology（华南理工大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局信息通信研究院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）
Retrospective artifact correction (RAC) improves image quality post acquisition and enhances image usability. Recent machine learning driven techniques for RAC are predominantly based on supervised learning and therefore practical utility can be limited as data with paired artifact-free and artifact-corrupted images are typically insufficient or even non-existent. Here we show that unwanted image artifacts can be disentangled and removed from an image via an RAC neural network learned with unpaired data. This implies that our method does not require matching artifact-corrupted data to be eithe…
The University of Tokyo（东京大学）；Peking University（北京大学）；University of Waterloo（滑铁卢大学）
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and self-supervised learning of deep neural networks. We analyze the training dynamics of deep networks on training data that are corrupted by, e.g., random noise and adversarial examples. Our analysis shows that model predictions are able to magnify useful underlying information in data and this phenomenon occurs broadly even in the absence of any label information, highlig…
Optical Coherence Tomography (OCT) is pervasive in both the research and clinical practice of Ophthalmology. However, OCT images are strongly corrupted by noise, limiting their interpretation. Current OCT denoisers leverage assumptions on noise distributions or generate targets for training deep supervised denoisers via averaging of repeat acquisitions. However, recent self-supervised advances allow the training of deep denoising networks using only repeat acquisitions without clean targets as ground truth, reducing the burden of supervised learning. Despite the clear advantages of self-superv…
Video monitoring of traffic is useful for traffic management and control, traffic counting, and traffic law enforcement. However, traffic monitoring during inclement weather such as rain is a challenging task because video quality is corrupted by streaks of falling rain on the video image, and this hinders reliable characterization not only of the road environment but also of road-user behavior during such adverse weather events. This study proposes a two-stage self-supervised learning method to remove rain streaks in traffic videos. The first and second stages address intra- and inter-frame n…
Michigan State University（密歇根州立大学）；University of Michigan - Shanghai Jiao Tong University Joint Institute（密歇根大学-上海交通大学联合学院）；Shanghai Jiao Tong University（上海交通大学）
Many techniques have been proposed for image reconstruction in medical imaging that aim to recover high-quality images especially from limited or corrupted measurements. Model-based reconstruction methods have been particularly popular (e.g., in magnetic resonance imaging and tomographic modalities) and exploit models of the imaging system's physics together with statistical models of measurements, noise and often relatively simple object priors or regularizers. For example, sparsity or low-rankness based regularizers have been widely used for image reconstruction from limited data such as in …
Self-Supervised Slice-to-Volume Reconstruction with Gaussian Representations for Fetal MRI
Department of Electrical and Electronic Engineering and I-X, Imperial College London（伦敦帝国理工学院电气与电子工程系及I-X）；Trinity College Institute of Neuroscience, Trinity College Dublin（都柏林圣三一学院神经科学研究所）
Supervised neural networks are known to achieve excellent results in various image restoration tasks. However, such training requires datasets composed of pairs of corrupted images and their corresponding ground truth targets. Unfortunately, such data is not available in many applications. For the task of image denoising in which the noise statistics is unknown, several self-supervised training methods have been proposed for overcoming this difficulty. Some of these require knowledge of the noise model, while others assume that the contaminating noise is uncorrelated, both assumptions are too …
We address the problem of depth and ego-motion estimation from image sequences. Recent advances in the domain propose to train a deep learning model for both tasks using image reconstruction in a self-supervised manner. We revise the assumptions and the limitations of the current approaches and propose two improvements to boost the performance of the depth and ego-motion estimation. We first use Lie group properties to enforce the geometric consistency between images in the sequence and their reconstructions. We then propose a mechanism to pay an attention to image regions where the image reco…
University of Science Technology of China（中国科学技术大学）；Microsoft Cloud AI（微软云人工智能）
The fast evolution and widespread of deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Some works capture the features that are unrelated to method-specific artifacts, such as clues of blending boundary, accumulated up-sampling, to strengthen the generalization ability. However, the effectiveness of these methods can be easily corrupted by post-processing operations such as compression. Inspired by transfer learning, neural networks pre-trained on other large-scale face-related tasks may provide useful features for deepfake detecti…
We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution. Given a corrupted input image, the model synthesizes a spatially varying linear filter which, when applied to the input image, reconstructs the desired output. The model parameters are learned using supervised or self-supervised training. We test this model on three tasks: non-uniform motion blur removal, lossy-compression artifact reduction and single image super resolution. We demonstrate that our model substantially outperforms state-of-the-art methods …
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Kim Jaechul Graduate School of AI（金在哲人工智能研究生院）
Recently, there has been extensive research interest in training deep networks to denoise images without clean reference. However, the representative approaches such as Noise2Noise, Noise2Void, Stein's unbiased risk estimator (SURE), etc. seem to differ from one another and it is difficult to find the coherent mathematical structure. To address this, here we present a novel approach, called Noise2Score, which reveals a missing link in order to unite these seemingly different approaches. Specifically, we show that image denoising problems without clean images can be addressed by finding the mod…
Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations
Department of Electrical and Computer Engineering, Seoul National University（电气电子工程系，首尔国立大学）；INMC & IPAI, Seoul National University（INMC与IPAI，首尔国立大学）；Division of Computer Engineering, Hankuk University of Foreign Studies（计算机工程系，韩文大学）；Department of Radiology, Johns Hopkins University School of Medicine（放射科，约翰霍普金斯大学医学院）
With the advent of recent advances in unsupervised learning, efficient training of a deep network for image denoising without pairs of noisy and clean images has become feasible. However, most current unsupervised denoising methods are built on the assumption of zero-mean noise under the signal-independent condition. This assumption causes blind denoising techniques to suffer brightness shifting problems on images that are greatly corrupted by extreme noise such as salt-and-pepper noise. Moreover, most blind denoising methods require a random masking scheme for training to ensure the invarianc…
Motivated by the fact that forward and backward passes of a deep network naturally form symmetric mappings between input and output representations, we introduce a simple yet effective self-supervised vision model pretraining framework inspired by energy-based models (EBMs). In the proposed framework, we model energy estimation and data restoration as the forward and backward passes of a single network without any auxiliary components, e.g., an extra decoder. For the forward pass, we fit a network to an energy function that assigns low energy scores to samples that belong to an unlabeled datas…
MID: A Self-supervised Multimodal Iterative Denoising Framework
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（自动化与智能感知学院，上海交通大学）；Key Laboratory of System Control and Information Processing, Ministry of Education of China（系统控制与信息处理重点实验室，中华人民共和国教育部）
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
Southern University of Science and Technology（南方科技大学）；The Hong Kong University of Science and Technology（香港科技大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Hong Kong Baptist University（香港 Baptist 大学）
Zhejiang University（浙江大学）；University of Notre Dame（圣母大学）
In clinical practice, medical image interpretation often involves multi-labeled classification, since the affected parts of a patient tend to present multiple symptoms or comorbidities. Recently, deep learning based frameworks have attained expert-level performance on medical image interpretation, which can be attributed partially to large amounts of accurate annotations. However, manually annotating massive amounts of medical images is impractical, while automatic annotation is fast but imprecise (possibly introducing corrupted labels). In this work, we propose a new regularization approach, …
Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning
Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）；School of Electronic and Information Engineering, South China University of Technology（电子与信息工程学院，华南理工大学）
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）
Remote sensing images are used for a variety of analyses, from agricultural monitoring, to disaster relief, to resource planning, among others. The images can be corrupted due to a number of reasons, including instrument errors and natural obstacles such as clouds. We present here a novel approach for reconstruction of missing information in such cases using only the corrupted image as the input. The Deep Image Prior methodology eliminates the need for a pre-trained network or an image database. It is shown that the approach easily beats the performance of traditional single-image methods.
