Image classification is a challenging problem for computer in reality. Large numbers of methods can achieve satisfying performances with sufficient labeled images. However, labeled images are still highly limited for certain image classification tasks. Instead, lots of unlabeled images are available and easy to be obtained. Therefore, making full use of the available unlabeled data can be a potential way to further improve the performance of current image classification methods. In this paper, we propose a discriminative semi-supervised sparse representation algorithm for image classification. In the algorithm, the classification process is combined with the sparse coding to learn a data-driven linear classifier. To obtain discriminative predictions, the predicted labels are regularized with three graphs, i.e., the global manifold structure graph, the within-class graph and the between-classes graph. The constructed graphs are able to extract structure information included in both the labeled and unlabeled data. Moreover, the proposed method is extended to a kernel version for dealing with data that cannot be linearly classified. Accordingly, efficient algorithms are developed to solve the corresponding optimization problems. Experimental results on several challenging databases demonstrate that the proposed algorithm achieves excellent performances compared with related popular methods.
In a deep neural network (DNN), the number of the parameters is usually huge to get high learning performances. For that reason, it costs a lot of memory and substantial computational resources, and also causes overfitting. It is known that some parameters are redundant and can be removed from the network without decreasing performance. Many sparse regularization criteria have been proposed to solve this problem. In a convolutional neural network (CNN), group sparse regularizations are often used to remove unnecessary subsets of the weights, such as filters or channels. When we apply a group s…
Recent advances in semi-supervised learning have shown tremendous potential in overcoming a major barrier to the success of modern machine learning algorithms: access to vast amounts of human-labeled training data. Previous algorithms based on consistency regularization can harness the abundance of unlabeled data to produce impressive results on a number of semi-supervised benchmarks, approaching the performance of strong supervised baselines using only a fraction of the available labeled data. In this work, we challenge the long-standing success of consistency regularization by introducing se…
Philips Medical Systems Technologies Ltd.（飞利浦医疗系统科技有限公司）
Deep sparse auto-encoders with mixed structure regularization (MSR) in addition to explicit sparsity regularization term and stochastic corruption of the input data with Gaussian noise have the potential to improve unsupervised abnormality detection. Unsupervised abnormality detection based on identifying outliers using deep sparse auto-encoders is a very appealing approach for medical computer aided detection systems as it requires only healthy data for training rather than expert annotated abnormality. In the task of detecting coronary artery disease from Coronary Computed Tomography Angiogr…
Center for Data Science（数据科学中心）；New York University（纽约大学）；Courant Institute（库朗研究所）；Meta AI - FAIR（Meta人工智能实验室——基础人工智能研究团队）
Sparse representations of images are useful in many computer vision applications. Sparse coding with an $l_1$ penalty and a learned linear dictionary requires regularization of the dictionary to prevent a collapse in the $l_1$ norms of the codes. Typically, this regularization entails bounding the Euclidean norms of the dictionary's elements. In this work, we propose a novel sparse coding protocol which prevents a collapse in the codes without the need to regularize the decoder. Our method regularizes the codes directly so that each latent code component has variance greater than a fixed thres…
Since the convolutional neural networks are often trained with redundant parameters, it is possible to reduce redundant kernels or filters to obtain a compact network without dropping the classification accuracy. In this paper, we propose a filter pruning method using the hierarchical group sparse regularization. It is shown in our previous work that the hierarchical group sparse regularization is effective in obtaining sparse networks in which filters connected to unnecessary channels are automatically close to zero. After training the convolutional neural network with the hierarchical group …
Polytechnic Institute of New York University（纽约大学理工学院）
Convex optimization with sparsity-promoting convex regularization is a standard approach for estimating sparse signals in noise. In order to promote sparsity more strongly than convex regularization, it is also standard practice to employ non-convex optimization. In this paper, we take a third approach. We utilize a non-convex regularization term chosen such that the total cost function (consisting of data consistency and regularization terms) is convex. Therefore, sparsity is more strongly promoted than in the standard convex formulation, but without sacrificing the attractive aspects of conv…
Baidu Research（百度研究院）；University of Oregon（俄勒冈大学）；University of Macau（澳门大学）
While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is randomly initialized. In this work, we consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain as well as labeled/unlabeled data in the target domain. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization th…
Compared with standard supervised learning, the key difficulty in semi-supervised learning is how to make full use of the unlabeled data. A recently proposed method, virtual adversarial training (VAT), smartly performs adversarial training without label information to impose a local smoothness on the classifier, which is especially beneficial to semi-supervised learning. In this work, we propose tangent-normal adversarial regularization (TNAR) as an extension of VAT by taking the data manifold into consideration. The proposed TNAR is composed by two complementary parts, the tangent adversarial…
Space Applications Centre（空间应用中心）；Indian Space Research Organization（印度空间研究组织）
Despite numerous attempts sought to provide empirical evidence of adversarial regularization outperforming sole supervision, the theoretical understanding of such phenomena remains elusive. In this study, we aim to resolve whether adversarial regularization indeed performs better than sole supervision at a fundamental level. To bring this insight into fruition, we study vanishing gradient issue, asymptotic iteration complexity, gradient flow and provable convergence in the context of sole supervision and adversarial regularization. The key ingredient is a theoretical justification supported by…
Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their limitations. CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings. The two representations interact with each other to jointly evolve. The embeddings impose a smoothness constraint on the class probabilities to improve the pseudo-labels, whereas the pseudo-labels regularize the structure of th…
Lancaster University（兰卡斯特大学）；Harvard SEAS（哈佛大学工程与应用科学学院）；MPI for Informatics（马克斯·普朗克信息学研究所）
In many learning tasks, the structure of the target space of a function holds rich information about the relationships between evaluations of functions on different data points. Existing approaches attempt to exploit this relationship information implicitly by enforcing smoothness on function evaluations only. However, what happens if we explicitly regularize the relationships between function evaluations? Inspired by homophily, we regularize based on a smooth relationship function, either defined from the data or with labels. In experiments, we demonstrate that this significantly improves the…
Autodesk AI Lab（欧特克人工智能实验室）；Imperial College London（伦敦帝国理工学院）
Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate learning group-disentangled representations for groups of factors with weak supervision. Existing techniques to address this challenge merely constrain the approximate posterior by averaging over observations of a shared group. As a result, observations with a common set of variations are encoded to distinct latent representations, reducing their capacity to disentangle and generalize to downstream tasks. In contrast…
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Recent advances in contrastive learning have enlightened diverse applications across various semi-supervised fields. Jointly training supervised learning and unsupervised learning with a shared feature encoder becomes a common scheme. Though it benefits from taking advantage of both feature-dependent information from self-supervised learning and label-dependent information from supervised learning, this scheme remains suffering from bias of the classifier. In this work, we systematically explore the relationship between self-supervised learning and supervised learning, and study how self-super…
Facebook AI Research（脸书人工智能研究院）；Inria, École normale supérieure, CNRS, PSL Research University（法国国家信息与自动化研究所、巴黎高等师范学院、法国国家科学研究中心、巴黎文理研究大学）；Courant Institute, New York University（纽约大学库朗数学科学研究所）；Center for Data Science, New York University（纽约大学数据科学中心）
Recent self-supervised methods for image representation learning are based on maximizing the agreement between embedding vectors from different views of the same image. A trivial solution is obtained when the encoder outputs constant vectors. This collapse problem is often avoided through implicit biases in the learning architecture, that often lack a clear justification or interpretation. In this paper, we introduce VICReg (Variance-Invariance-Covariance Regularization), a method that explicitly avoids the collapse problem with a simple regularization term on the variance of the embeddings al…
Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However, their performance still lags behind the state-of-the-art non-GAN based SSL approaches. We identify that the main reason for this is the lack of consistency in class probability predictions on the same image under local perturbations. Following the general literature, we address this issue via label consistency regularization, which enforces the class probabili…
Universität Heidelberg（海德堡大学）；Hochschule Darmstadt（达姆施塔特应用技术大学）；Helmholtz Zentrum München（慕尼黑亥姆霍兹中心）
In this paper, we consider the sparse regularization of manifold-valued data with respect to an interpolatory wavelet/multiscale transform. We propose and study variational models for this task and provide results on their well-posedness. We present algorithms for a numerical realization of these models in the manifold setup. Further, we provide experimental results to show the potential of the proposed schemes for applications.
Sparse modeling is one of the efficient techniques for imaging that allows recovering lost information. In this paper, we present a novel iterative phase-retrieval algorithm using a sparse representation of the object amplitude and phase. The algorithm is derived in terms of a constrained maximum likelihood, where the wave field reconstruction is performed using a number of noisy intensity-only observations with a zero-mean additive Gaussian noise. The developed algorithm enables the optimal solution for the object wave field reconstruction. Our goal is an improvement of the reconstruction qua…
An efficient spatial regularization method using superpixel segmentation and graph Laplacian regularization is proposed for sparse hyperspectral unmixing method. Since it is likely to find spectrally similar pixels in a homogeneous region, we use a superpixel segmentation algorithm to extract the homogeneous regions by considering the image boundaries. We first extract the homogeneous regions, which are called superpixels, then a weighted graph in each superpixel is constructed by selecting $K$-nearest pixels in each superpixel. Each node in the graph represents the spectrum of a pixel and edg…
Federal University of Santa Catarina（圣卡塔琳娜联邦大学）；CNRS（法国国家科学研究中心）；OCA（蔚蓝海岸天文台）
Sparse hyperspectral unmixing from large spectral libraries has been considered to circumvent limitations of endmember extraction algorithms in many applications. This strategy often leads to ill-posed inverse problems, which can benefit from spatial regularization strategies. While existing spatial regularization methods improve the problem conditioning and promote piecewise smooth solutions, they lead to large nonsmooth optimization problems. Thus, efficiently introducing spatial context in the unmixing problem remains a challenge, and a necessity for many real world applications. In this pa…
Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under different input perturbations, particularly has shown to provide state-of-the art results in a semi-supervised framework. However, most of these method have been limited to classification and segmentation applications. We propose Transformation Consistency Regularization, which delves into a more challenging setting of image-to-image translation, which remains u…
Xidian University（西安电子科技大学）；The Hong Kong Polytechnic University（香港理工大学）；McMaster University（麦克马斯特大学）
As a powerful statistical image modeling technique, sparse representation has been successfully used in various image restoration applications. The success of sparse representation owes to the development of l1-norm optimization techniques, and the fact that natural images are intrinsically sparse in some domain. The image restoration quality largely depends on whether the employed sparse domain can represent well the underlying image. Considering that the contents can vary significantly across different images or different patches in a single image, we propose to learn various sets of bases f…
The scarcity of pixel-level annotation is a prevalent problem in medical image segmentation tasks. In this paper, we introduce a novel regularization strategy involving interpolation-based mixing for semi-supervised medical image segmentation. The proposed method is a new consistency regularization strategy that encourages segmentation of interpolation of two unlabelled data to be consistent with the interpolation of segmentation maps of those data. This method represents a specific type of data-adaptive regularization paradigm which aids to minimize the overfitting of labelled data under high…
Institut LIST, CEA（法国原子能与替代能源委员会 LIST 研究所）；Université Paris-Saclay（巴黎-萨克雷大学）；Astrophysics Department, CEA（法国原子能与替代能源委员会天体物理部）
Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of labelled samples per class to achieve an acceptable result. In order to deal with databases which have just a few labelled samples per class, semi-supervised learning, which also exploits unlabelled samples in training phase is used. Indeed, unlabelled samples can help to regularize the learning model, yielding an improvement of classification accuracy. In this paper, we propose …
Computer Vision Center (CVC)（计算机视觉中心）；Universitat Autonoma of Barcelona (UAB)（巴塞罗那自治大学）；Media Integration and Communication Center（媒体整合与传播中心）
Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable to acquire new knowledge incrementally -- they are, in fact, mostly used only as a pre-training phase over IID data. In this work we investigate self-supervised methods in continual learning regimes without any replay mechanism. We show that naive functional regularization, also known as feature distillation, leads to lower plasticity and limits continual learning performance. Instead, we propose Projected Functional …
University of California, Merced（加州大学默塞德分校）；eBay Inc.（eBay公司）；NEC Labs America（美国NEC实验室）；Google Research（谷歌研究院）
Obtaining object response maps is one important step to achieve weakly-supervised semantic segmentation using image-level labels. However, existing methods rely on the classification task, which could result in a response map only attending on discriminative object regions as the network does not need to see the entire object for optimizing the classification loss. To tackle this issue, we propose a principled and end-to-end train-able framework to allow the network to pay attention to other parts of the object, while producing a more complete and uniform response map. Specifically, we introdu…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Consistency regularization is one of the most widely-used techniques for semi-supervised learning (SSL). Generally, the aim is to train a model that is invariant to various data augmentations. In this paper, we revisit this idea and find that enforcing invariance by decreasing distances between features from differently augmented images leads to improved performance. However, encouraging equivariance instead, by increasing the feature distance, further improves performance. To this end, we propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLos…
School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）；Center for Machine Vision and Signal Analysis, University of Oulu（奥卢大学机器视觉与信号分析中心）
Patch-based sparse representation modeling has shown great potential in image compressive sensing (CS) reconstruction. However, this model usually suffers from some limits, such as dictionary learning with great computational complexity, neglecting the relationship among similar patches. In this paper, a group-based sparse representation method with non-convex regularization (GSR-NCR) for image CS reconstruction is proposed. In GSR-NCR, the local sparsity and nonlocal self-similarity of images is simultaneously considered in a unified framework. Different from the previous methods based on spa…
Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data. Different from existing works, we present a novel way to obtain the surrogate supervision signal based on high-level feature maps under consistency regularization. In this paper, we propose a Spatio-Temporal Consistency Regularization between different output features generated from a siamese network including a clean path fed with original video and a noise path fed with the corresponding augmented vi…
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；imec-IDLab
One of the most common problems of weakly supervised object localization is that of inaccurate object coverage. In the context of state-of-the-art methods based on Class Activation Mapping, this is caused either by localization maps which focus, exclusively, on the most discriminative region of the objects of interest or by activations occurring in background regions. To address these two problems, we propose two representation regularization mechanisms: Full Region Regularizationwhich tries to maximize the coverage of the localization map inside the object region, and Common Region Regulariza…
We present a supervised hyperspectral image segmentation algorithm based on a convex formulation of a marginal maximum a posteriori segmentation with hidden fields and structure tensor regularization: Segmentation via the Constraint Split Augmented Lagrangian Shrinkage by Structure Tensor Regularization (SegSALSA-STR). This formulation avoids the generally discrete nature of segmentation problems and the inherent NP-hardness of the integer optimization associated. We extend the Segmentation via the Constraint Split Augmented Lagrangian Shrinkage (SegSALSA) algorithm by generalizing the vectori…
Rochester Institute of Technology（罗切斯特理工学院）；Chosun University（朝鲜大学）
Unpaired image denoising has achieved promising development over the last few years. Regardless of the performance, methods tend to heavily rely on underlying noise properties or any assumption which is not always practical. Alternatively, if we can ground the problem from a structural perspective rather than noise statistics, we can achieve a more robust solution. with such motivation, we propose a self-supervised denoising scheme that is unpaired and relies on spatial degradation followed by a regularized refinement. Our method shows considerable improvement over previous methods and exhibit…
Laboratoire AIM, UMR CEA-CNRS-Paris 7（AIM实验室，CEA-CNRS-巴黎第七大学联合研究单位）；CEA Saclay（法国原子能和替代能源委员会萨克莱研究中心）
In large-scale spatial surveys, such as the forthcoming ESA Euclid mission, images may be undersampled due to the optical sensors sizes. Therefore, one may consider using a super-resolution (SR) method to recover aliased frequencies, prior to further analysis. This is particularly relevant for point-source images, which provide direct measurements of the instrument point-spread function (PSF). We introduce SPRITE, SParse Recovery of InsTrumental rEsponse, which is an SR algorithm using a sparse analysis prior. We show that such a prior provides significant improvements over existing methods, e…
Korea University（高丽大学）；NAVER AI Lab（NAVER人工智能实验室）；Samsung Electro-Mechanics（三星电机）
We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label, dubbed ConMatch. While the latest semi-supervised learning methods use weakly- and strongly-augmented views of an image to define a directional consistency loss, how to define such direction for the consistency regularization between two strongly-augmented views remains unexplored. To account for this, we present novel confidence measures for pseudo-labels from s…
Self-Supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representation
Helmholtz Center Munich（慕尼黑亥姆霍兹中心）；Technical University of Munich（慕尼黑工业大学）；Imperial College London（伦敦帝国学院）；Millenium Institute for Intelligent Healthcare Engineering（千禧智能医疗工程研究所）；Pontificia Universidad Católica de Chile（智利天主教大学）；King’s College London（伦敦国王学院）
PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting
School of Computer Science, Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学深圳校区计算机科学学院，中国）；Pengcheng Laboratory, Shenzhen, China（鹏城实验室，中国）；Smart Coding Institute, Pengcheng Laboratory, Shenzhen, China（鹏城实验室智能编码研究所，中国）；School of Computer Science, Harbin Institute of Technology, Harbin, China（哈尔滨工业大学计算机科学学院，中国）
Boston University（波士顿大学）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
Semi-supervised learning (SSL) is an effective means to leverage unlabeled data to improve a model's performance. Typical SSL methods like FixMatch assume that labeled and unlabeled data share the same label space. However, in practice, unlabeled data can contain categories unseen in the labeled set, i.e., outliers, which can significantly harm the performance of SSL algorithms. To address this problem, we propose a novel Open-set Semi-Supervised Learning (OSSL) approach called OpenMatch. Learning representations of inliers while rejecting outliers is essential for the success of OSSL. To this…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））
Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional sparse coding, which aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminative. Experimental results show that using supervised convolutional learning results in two key advant…
Singtel Cognitive and Artificial Intelligence Lab for Enterprises, Nanyang Technological University（新加坡南洋理工大学新电信企业认知与人工智能实验室）
Semi-supervised semantic segmentation learns from small amounts of labelled images and large amounts of unlabelled images, which has witnessed impressive progress with the recent advance of deep neural networks. However, it often suffers from severe class-bias problem while exploring the unlabelled images, largely due to the clear pixel-wise class imbalance in the labelled images. This paper presents an unbiased subclass regularization network (USRN) that alleviates the class imbalance issue by learning class-unbiased segmentation from balanced subclass distributions. We build the balanced sub…
Harbin Institute of Technology（哈尔滨工业大学）；Peking University（北京大学）
In this paper, we propose a novel image interpolation algorithm, which is formulated via combining both the local autoregressive (AR) model and the nonlocal adaptive 3-D sparse model as regularized constraints under the regularization framework. Estimating the high-resolution image by the local AR regularization is different from these conventional AR models, which weighted calculates the interpolation coefficients without considering the rough structural similarity between the low-resolution (LR) and high-resolution (HR) images. Then the nonlocal adaptive 3-D sparse model is formulated to reg…
An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such constraints in the training of convolutional neural networks (CNN), however this has so far been done within a continuous optimization framework. Yet, various segmentation constraints and regularization can be modeled and optimized more efficiently in a discrete formulation. This paper proposes a method, based on the alternating direction method of multipliers (ADMM) algorithm, to train a CNN with discrete constraints an…
FZI Research Center for Information Technology（FZI信息技术研究中心）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院（KIT））
We present a self-supervised approach to estimate flow in camera image and top-view grid map sequences using fully convolutional neural networks in the domain of automated driving. We extend existing approaches for self-supervised optical flow estimation by adding a regularizer expressing motion consistency assuming a static environment. However, as this assumption is violated for other moving traffic participants we also estimate a mask to scale this regularization. Adding a regularization towards motion consistency improves convergence and flow estimation accuracy. Furthermore, we scale the …
Institute of Optics and Electronics, Chinese Academy of Sciences（中国科学院光电技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Image quality is the basis of image communication and understanding tasks. Due to the blur and noise effects caused by imaging, transmission and other processes, the image quality is degraded. Blind image restoration is widely used to improve image quality, where the main goal is to faithfully estimate the blur kernel and the latent sharp image. In this study, based on experimental observation and research, an adaptively sparse regularized minimization method is originally proposed. The high-order gradients combine with low-order ones to form a hybrid regularization term, and an adaptive opera…
