Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident predictions as pseudo-labels for retraining. However, since pseudo-labels can be noisy, self-training can put overconfident label belief on wrong classes, leading to deviated solutions with propagated errors. To address the problem, we propose a confidence regularized self-training (CRST) framework, formulated as regularized self-training. Our method treats pseudo-labels as continuous latent variables jointly optimized via alternating optimization. We propose two types of confidence regularization: label regularization (LR) and model regularization (MR). CRST-LR generates soft pseudo-labels while CRST-MR encourages the smoothness on network output. Extensive experiments on image classification and semantic segmentation show that CRSTs outperform their non-regularized counterpart with state-of-the-art performance. The code and models of this work are available at https://github.com/yzou2/CRST.
We propose $\textit{Mish}$, a novel self-regularized non-monotonic activation function which can be mathematically defined as: $f(x)=x\tanh(softplus(x))$. As activation functions play a crucial role in the performance and training dynamics in neural networks, we validated experimentally on several well-known benchmarks against the best combinations of architectures and activation functions. We also observe that data augmentation techniques have a favorable effect on benchmarks like ImageNet-1k and MS-COCO across multiple architectures. For example, Mish outperformed Leaky ReLU on YOLOv4 with a…
National University of Singapore（新加坡国立大学）；Chinese Academy of Sciences（中国科学院）；SEA AI Lab（SEA AI实验室）
Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature space. During deployment, the common practice is to directly fine-tune CSL models with cross-entropy, which however may not be the best strategy in practice. Although cross-entropy tends to separate inter-class features, the resulting models still have limited capability for reducing intra-class feature scattering that exists in CSL models. In this paper, we in…
The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties in generalizing to unseen object categories. Therefore, few-shot segmentation has been developed to perform segmentation with just a few annotated examples. In this work, we tackle the few-shot segmentation using a self-regularized prototypical network (SRPNet) based on prototype extraction for better utilization of the support information. The proposed SRPNet extracts class-specific prototype representations from support images and generates segmentation…
East China Normal University（华东师范大学）；Huashan Hospital, Fudan University（复旦大学附属华山医院）
Medical image segmentation is one of the fundamental problems for artificial intelligence-based clinical decision systems. Current automatic medical image segmentation methods are often failed to meet clinical requirements. As such, a series of interactive segmentation algorithms are proposed to utilize expert correction information. However, existing methods suffer from some segmentation refining failure problems after long-term interactions and some cost problems from expert annotation, which hinder clinical applications. This paper proposes an interactive segmentation framework, called inte…
SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation
School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；McKeley School of Engineering, Washington University in St. Louis（圣路易斯华盛顿大学麦凯莱工程学院）；School of Computing, Clemson University（克莱姆森大学计算学院）
Information Technology University（信息技术大学）；Facebook（脸书）
This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to greedily learn the representations that capture inter-class variations in order to determine the decision (class) boundary. Due to the domain shift, this decision boundary is unaligned in the target domain, resulting in noisy pseudo labels adversely affecting self-supervised domain adaptation. To overcome this limitation, along with capturing inter-class variation…
Beijing University of Posts and Telecommunications（北京邮电大学）
Self-regularized low-light image enhancement does not require any normal-light image in training, thereby freeing from the chains on paired or unpaired low-/normal-images. However, existing methods suffer color deviation and fail to generalize to various lighting conditions. This paper presents a novel self-regularized method based on Retinex, which, inspired by HSV, preserves all colors (Hue, Saturation) and only integrates Retinex theory into brightness (Value). We build a reflectance estimation network by restricting the consistency of reflectances embedded in both the original and a novel …
Sun Yat-sen University（中山大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；University of Technology Sydney（悉尼科技大学）；Oxford University（牛津大学）
Automatic data augmentation (AutoAugment) strategies are indispensable in supervised data-efficient training protocols of vision transformers, and have led to state-of-the-art results in supervised learning. Despite the success, its development and application on self-supervised vision transformers have been hindered by several barriers, including the high search cost, the lack of supervision, and the unsuitable search space. In this work, we propose AutoView, a self-regularized adversarial AutoAugment method, to learn views for self-supervised vision transformers, by addressing the above barr…
A novel algorithm is proposed to downscale microwave brightness temperatures ($\mathrm{T_B}$), at scales of 10-40 km such as those from the Soil Moisture Active Passive mission to a resolution meaningful for hydrological and agricultural applications. This algorithm, called Self-Regularized Regressive Models (SRRM), uses auxiliary variables correlated to $\mathrm{T_B}$ along-with a limited set of \textit{in-situ} SM observations, which are converted to high resolution $\mathrm{T_B}$ observations using biophysical models. It includes an information-theoretic clustering step based on all auxilia…
Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions, such as the availability of all views in training and inference time. In this work, the problem of multiview self-supervised learning (MV-SSL) is investigated, where only image to object association is given. Given this setup, a novel surrogate task for self-supervised learning is proposed by pursuing "object invariant" representation. This is solved by random…
Convolutional Neural Networks (CNN) have shown promising results for displacement estimation in UltraSound Elastography (USE). Many modifications have been proposed to improve the displacement estimation of CNNs for USE in the axial direction. However, the lateral strain, which is essential in several downstream tasks such as the inverse problem of elasticity imaging, remains a challenge. The lateral strain estimation is complicated since the motion and the sampling frequency in this direction are substantially lower than the axial one, and a lack of carrier signal in this direction. In comput…
Hunan University of Science and Technology（湖南科技大学）；Nanjing First Hospital, Nanjing Medical University（南京医科大学附属南京第一医院）；University of Macau（澳门大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）
Compressive sensing (CS) based computed tomography (CT) image reconstruction aims at reducing the radiation risk through sparse-view projection data. It is usually challenging to achieve satisfying image quality from incomplete projections. Recently, the nonconvex ${L_ {1/2}} $-norm has achieved promising performance in sparse recovery, while the applications on imaging are unsatisfactory due to its nonconvexity. In this paper, we develop a ${L_ {1/2}} $-regularized nonlocal self-similarity (NSS) denoiser for CT reconstruction problem, which integrates low-rank approximation with group sparse …
Estimating the confidence of disparity maps inferred by a stereo algorithm has become a very relevant task in the years, due to the increasing number of applications leveraging such cue. Although self-supervised learning has recently spread across many computer vision tasks, it has been barely considered in the field of confidence estimation. In this paper, we propose a flexible and lightweight solution enabling self-adapting confidence estimation agnostic to the stereo algorithm or network. Our approach relies on the minimum information available in any stereo setup (i.e., the input stereo pa…
Self-Aligning Depth-regularized Radiance Fields for Asynchronous RGB-D Sequences
AIR, Tsinghua University（清华大学AIR）；Beijing Institute of Technology（北京理工大学）；Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所智能计算系统研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；Imperial College London（伦敦帝国学院）；Beihang University（北京航空航天大学）
LDReg: Local Dimensionality Regularized Self-Supervised Learning
School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系统学院）；University of Southern Denmark（南丹麦大学）；School of Computer Science, Fudan University（复旦大学计算机科学学院）；New Jersey Institute of Technology（新泽西理工学院）
In this paper, we aim to address the challenging task of semantic matching where matching ambiguity is difficult to resolve even with learned deep features. We tackle this problem by taking into account the confidence in predictions and develop a novel refinement strategy to correct partial matching errors. Specifically, we introduce a Confidence-Aware Semantic Matching Network (CAMNet) which instantiates two key ideas of our approach. First, we propose to estimate a dense confidence map for a matching prediction through self-supervised learning. Second, based on the estimated confidence, we r…
Bournemouth University（伯恩茅斯大学）；University of Chester（切斯特大学）
Convolutional Neural Networks (CNNs) need large amounts of data with ground truth annotation, which is a challenging problem that has limited the development and fast deployment of CNNs for many computer vision tasks. We propose a novel framework for depth estimation from monocular images with corresponding confidence in a self-supervised manner. A fully differential patch-based cost function is proposed by using the Zero-Mean Normalized Cross Correlation (ZNCC) that takes multi-scale patches as a matching strategy. This approach greatly increases the accuracy and robustness of the depth learn…
I2R, A-STAR（A*STAR信息通信研究所）；South China University of Technology（华南理工大学）；Southwest Jiaotong University（西南交通大学）
Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available, and instant inference on the target domain is required. Despite many efforts into TTT, there is a confusion over the experimental settings, thus leading to unfair comparisons. In this work, we first revisit TTT assumptions and categorize TTT protocols by two key factors. Among the multiple protocols, we adopt a realistic sequential test-time training (sTTT)…
SenseTime Research（商汤科技研究院）；Rice University（莱斯大学）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）
This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL benefits from fast and low-cost data collection, noises in web labels hinder better performance of the image classification model. To alleviate this problem, in recent works, self-label supervised loss $\mathcal{L}_s$ is utilized together with webly supervised loss $\mathcal{L}_w$. $\mathcal{L}_s$ relies on pseudo labels predicted by the model itself. Since the correctness of the web label or pseudo label is usually …
SAME++: A Self-supervised Anatomical eMbeddings Enhanced medical image registration framework using stable sampling and regularized transformation
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Alibaba Group（阿里巴巴集团）；Johns Hopkins University（约翰斯·霍普金斯大学）；The First Affiliated Hospital of Zhejiang University（浙江大学附属第一医院）
