Existing image-to-image (I2I) translation methods achieve state-of-the-art performance by incorporating the patch-wise contrastive learning into Generative Adversarial Networks. However, patch-wise contrastive learning only focuses on the local content similarity but neglects the global structure constraint, which affects the quality of the generated images. In this paper, we propose a new unpaired I2I translation framework based on dual contrastive regularization and spectral normalization, namely SN-DCR. To maintain consistency of the global structure and texture, we design the dual contrastive regularization using different deep feature spaces respectively. In order to improve the global structure information of the generated images, we formulate a semantic contrastive loss to make the global semantic structure of the generated images similar to the real images from the target domain in the semantic feature space. We use Gram Matrices to extract the style of texture from images. Similarly, we design a style contrastive loss to improve the global texture information of the generated images. Moreover, to enhance the stability of the model, we employ the spectral normalized convolutional network in the design of our generator. We conduct comprehensive experiments to evaluate the effectiveness of SN-DCR, and the results prove that our method achieves SOTA in multiple tasks.
University of Science and Technology of China（中国科学技术大学）；JD Explore Academy（京东探索研究院）
Generative Adversarial Networks (GANs) have been widely applied in different scenarios thanks to the development of deep neural networks. The original GAN was proposed based on the non-parametric assumption of the infinite capacity of networks. However, it is still unknown whether GANs can fit the target distribution without any prior information. Due to the overconfident assumption, many issues remain unaddressed in GANs' training, such as non-convergence, mode collapses, gradient vanishing. Regularization and normalization are common methods of introducing prior information to stabilize trai…
Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence. However, the methods often ignore the diverse semantic relation within the images. To address this, here we propose a novel semantic relation consistency (SRC) regularization along with the decoupled contrastive learning, which utilize the diverse semantics by focusing on the heterogeneous semantics between the image patches of a single image. To further improve the performance, we present a hard negative mining by exploiting the …
Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization. In this work, we propose a simple, effective training stabilizer based on the notion of consistency regularization---a popular technique in the semi-supervised learning literature. In particular, we augment data passing into the GAN discriminator and penalize the sensitivity of …
Rethink Arbitrary Style Transfer with Transformer and Contrastive Learning
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；College of Computer Science and Technology, Zhejiang Gongshang University（浙江工商大学计算机科学与技术学院）
Generative adversarial networks (GANs) are known to benefit from regularization or normalization of their critic (discriminator) network during training. In this paper, we analyze the popular spectral normalization scheme, find a significant drawback and introduce sparsity aware normalization (SAN), a new alternative approach for stabilizing GAN training. As opposed to other normalization methods, our approach explicitly accounts for the sparse nature of the feature maps in convolutional networks with ReLU activations. We illustrate the effectiveness of our method through extensive experiments…
Data augmentations have been widely studied to improve the accuracy and robustness of classifiers. However, the potential of image augmentation in improving GAN models for image synthesis has not been thoroughly investigated in previous studies. In this work, we systematically study the effectiveness of various existing augmentation techniques for GAN training in a variety of settings. We provide insights and guidelines on how to augment images for both vanilla GANs and GANs with regularizations, improving the fidelity of the generated images substantially. Surprisingly, we find that vanilla G…
L2 regularization for weights in neural networks is widely used as a standard training trick. However, L2 regularization for gamma, a trainable parameter of batch normalization, remains an undiscussed mystery and is applied in different ways depending on the library and practitioner. In this paper, we study whether L2 regularization for gamma is valid. To explore this issue, we consider two approaches: 1) variance control to make the residual network behave like identity mapping and 2) stable optimization through the improvement of effective learning rate. Through two analyses, we specify the …
Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation in terms of learning stability and sample quality. However, Wasserstein GANs require the critic to be 1-Lipschitz, which is often enforced implicitly by penalizing the norm of its gradient, or by globally restricting its Lipschitz constant via weight normalization techniques. Training with a regularization term penalizing the violation of the Lipschitz constraint explicitly, in…
Jilin University（吉林大学）；Baidu Research（百度研究院）；National Engineering Laboratory for Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）
Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect predictions, and pixel-level contrastive regularization has memory and computational cost with O(pixel_num^2). To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC^2L) for semi-supervised semantic segmentation. Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to …
In this paper, we consider a problem of self-supervised learning for small-scale datasets based on contrastive loss between multiple views of the data, which demonstrates the state-of-the-art performance in classification task. Despite the reported results, such factors as the complexity of training requiring complex architectures, the needed number of views produced by data augmentation, and their impact on the classification accuracy are understudied problems. To establish the role of these factors, we consider an architecture of contrastive loss system such as SimCLR, where baseline model i…
Multi-Source Unsupervised Domain Adaptation (multi-source UDA) aims to learn a model from several labeled source domains while performing well on a different target domain where only unlabeled data are available at training time. To align source and target features distributions, several recent works use source and target explicit statistics matching such as features moments or class centroids. Yet, these approaches do not guarantee class conditional distributions alignment across domains. In this work, we propose a new framework called Contrastive Multi-Source Domain Adaptation (CMSDA) for mu…
Unsupervised domain adaptation (UDA) for semantic segmentation has been well-studied in recent years. However, most existing works largely neglect the local regional consistency across different domains and are less robust to changes in outdoor environments. In this paper, we propose a novel and fully end-to-end trainable approach, called regional contrastive consistency regularization (RCCR) for domain adaptive semantic segmentation. Our core idea is to pull the similar regional features extracted from the same location of different images, i.e., the original image and augmented image, to be …
Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Cambridge（剑桥大学）；The Hong Kong University of Science and Technology（香港科技大学）
IMT Atlantique（IMT大西洋高等矿业电信学校）；LaTIM UMR 1101, Inserm（LaTIM（法国国家健康与医学研究院1101联合研究单位））；Centre Hospitalier Régional et Universitaire (CHRU) Brest（布雷斯特大学中心医院）；SCMIA, Symbiosis International University（共生国际大学SCMIA）
Automatic segmentation of magnetic resonance (MR) images is crucial for morphological evaluation of the pediatric musculoskeletal system in clinical practice. However, the accuracy and generalization performance of individual segmentation models are limited due to the restricted amount of annotated pediatric data. Hence, we propose to train a segmentation model on multiple datasets, arising from different parts of the anatomy, in a multi-task and multi-domain learning framework. This approach allows to overcome the inherent scarcity of pediatric data while benefiting from a more robust shared …
Batch normalization (BN) has become a de facto standard for training deep convolutional networks. However, BN accounts for a significant fraction of training run-time and is difficult to accelerate, since it is a memory-bandwidth bounded operation. Such a drawback of BN motivates us to explore recently proposed weight normalization algorithms (WN algorithms), i.e. weight normalization, normalization propagation and weight normalization with translated ReLU. These algorithms don't slow-down training iterations and were experimentally shown to outperform BN on relatively small networks and datas…
Representation Alignment Contrastive Regularization for Multi-Object Tracking
College of Computer Science and Technology, Zhejiang Gongshang University（浙江工商大学计算机科学与技术学院）；Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology（浙江省大数据与未来电子商务技术重点实验室）；Zhejiang Uniview Technologies Co.,Ltd.（浙江宇视科技有限公司）
Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning
University of Chinese Academy of Sciences（中国科学院大学）；Hangzhou Dianzi University (HDU)（杭州电子科技大学）；Lishui Institute of HDU（杭州电子科技大学丽水研究院）；Key Laboratory of AI Safety of CAS（中国科学院人工智能安全重点实验室）；Institute of Computing Technology, Chinese Academy of Sciences (CAS)（中国科学院计算技术研究所）
RegBN: Batch Normalization of Multimodal Data with Regularization
Technical University of Munich (TUM)（慕尼黑工业大学（TUM））；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Lab for AI in Medical Imaging (AI-Med)（医学影像人工智能实验室）
In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, domain shift, may occur, which becomes a major factor impeding the generalization performance of the model. The research field to solve this problem is called domain generalization, and it alleviates the domain shift problem by extracting domain-invariant features explicitly or implicitly. In recent studies, contrastive learning-based domain generalization approa…
Nanjing University（南京大学）；University of Wollongong（伍伦贡大学）；University of Rochester（罗切斯特大学）
In recent years, a variety of contrastive learning based unsupervised visual representation learning methods have been designed and achieved great success in many visual tasks. Generally, these methods can be roughly classified into four categories: (1) standard contrastive methods with an InfoNCE like loss, such as MoCo and SimCLR; (2) non-contrastive methods with only positive pairs, such as BYOL and SimSiam; (3) whitening regularization based methods, such as W-MSE and VICReg; and (4) consistency regularization based methods, such as CO2. In this study, we present a new unified contrastive …
OSRAM GmbH（欧司朗有限公司）；Sapienza University of Rome（罗马智慧大学）
Contrastive losses yield state-of-the-art performance for person re-identification, face verification and few shot learning. They have recently outperformed the cross-entropy loss on classification at the ImageNet scale and outperformed all self-supervision prior results by a large margin (SimCLR). Simple and effective regularization techniques such as label smoothing and self-distillation do not apply anymore, because they act on multinomial label distributions, adopted in cross-entropy losses, and not on tuple comparative terms, which characterize the contrastive losses. Here we propose a no…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Pennsylvania（宾夕法尼亚大学）；Google Research（谷歌研究院）；Princeton University（普林斯顿大学）；Microsoft Research（微软研究院）
Normalization methods such as batch [Ioffe and Szegedy, 2015], weight [Salimansand Kingma, 2016], instance [Ulyanov et al., 2016], and layer normalization [Baet al., 2016] have been widely used in modern machine learning. Here, we study the weight normalization (WN) method [Salimans and Kingma, 2016] and a variant called reparametrized projected gradient descent (rPGD) for overparametrized least-squares regression. WN and rPGD reparametrize the weights with a scale g and a unit vector w and thus the objective function becomes non-convex. We show that this non-convex formulation has beneficial …
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…
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Tsinghua University（清华大学）
Image harmonization aims to achieve visual consistency in composite images by adapting a foreground to make it compatible with a background. However, existing methods always only use the real image as the positive sample to guide the training, and at most introduce the corresponding composite image as a single negative sample for an auxiliary constraint, which leads to limited distortion knowledge, and further causes a too large solution space, making the generated harmonized image distorted. Besides, none of them jointly constrain from the foreground self-style and foreground-background style…
Semi-supervised learning (SSL) has long been proved to be an effective technique to construct powerful models with limited labels. In the existing literature, consistency regularization-based methods, which force the perturbed samples to have similar predictions with the original ones have attracted much attention for their promising accuracy. However, we observe that, the performance of such methods decreases drastically when the labels get extremely limited, e.g., 2 or 3 labels for each category. Our empirical study finds that the main problem lies with the drifting of semantic information i…
Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
Huanjiang Laboratory, Zhuji, P.R. China and School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, P.R.China（湖南江实验室，浙江诸暨，中国 和 浙江大学航空宇航学院，杭州，中国）；School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, P.R.China（浙江大学航空宇航学院，杭州，中国）；Electrical and Computer Engineering Department, Hellenic Mediterranean University, Heraklion, Crete, Greece（希腊地中海大学电气与计算机工程系，赫拉克利翁，克里特，希腊）
Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization
Department of Computer Science and Engineering, University of Notre Dame（Notre Dame 大学计算机科学与工程系）；College of Engineering and Computer Science, VinUniversity（Vin大学工程与计算机科学学院）；Open Distributed Systems, Technical University Berlin（柏林技术大学开放分布式系统）
Annotated medical images are typically rarer than labeled natural images since they are limited by domain knowledge and privacy constraints. Recent advances in transfer and contrastive learning have provided effective solutions to tackle such issues from different perspectives. The state-of-the-art transfer learning (e.g., Big Transfer (BiT)) and contrastive learning (e.g., Simple Siamese Contrastive Learning (SimSiam)) approaches have been investigated independently, without considering the complementary nature of such techniques. It would be appealing to accelerate contrastive learning with …
A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging both to generically improve upon Batch Normalization and to understand the circumstances that lend themselves to other enhancements. In this paper, we identify four improvements to the generic form of Batch Normalization and the circumstances under which they work, yielding performance gains across all batch sizes while requiring no additional computation during training. These co…
This paper introduces SelfMatch, a semi-supervised learning method that combines the power of contrastive self-supervised learning and consistency regularization. SelfMatch consists of two stages: (1) self-supervised pre-training based on contrastive learning and (2) semi-supervised fine-tuning based on augmentation consistency regularization. We empirically demonstrate that SelfMatch achieves the state-of-the-art results on standard benchmark datasets such as CIFAR-10 and SVHN. For example, for CIFAR-10 with 40 labeled examples, SelfMatch achieves 93.19% accuracy that outperforms the strong p…
IMT Atlantique（大西洋国立高等矿业电信学校）；LaTIM UMR 1101, Inserm（法国国家健康与医学研究院LaTIM UMR 1101实验室）；Centre Hospitalier Régional et Universitaire (CHRU) de Brest（布雷斯特大学区域中心医院）；Fondation ILDYS（ILDYS基金会）；Symbiosis Center for Medical Image Analysis, Symbiosis International University（共生国际大学共生医学图像分析中心）
Clinical diagnosis of the pediatric musculoskeletal system relies on the analysis of medical imaging examinations. In the medical image processing pipeline, semantic segmentation using deep learning algorithms enables an automatic generation of patient-specific three-dimensional anatomical models which are crucial for morphological evaluation. However, the scarcity of pediatric imaging resources may result in reduced accuracy and generalization performance of individual deep segmentation models. In this study, we propose to design a novel multi-task, multi-domain learning framework in which a …
South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）；Ant Group（蚂蚁集团）
Recently self-supervised representation learning has drawn considerable attention from the scene text recognition community. Different from previous studies using contrastive learning, we tackle the issue from an alternative perspective, i.e., by formulating the representation learning scheme in a generative manner. Typically, the neighboring image patches among one text line tend to have similar styles, including the strokes, textures, colors, etc. Motivated by this common sense, we augment one image patch and use its neighboring patch as guidance to recover itself. Specifically, we propose a…
Universitas Indonesia（印度尼西亚大学）；Agency for the Assessment and Application of Technology (BPPT)（印度尼西亚技术与应用评估局（BPPT））
This study uses remote sensing technology that can provide information about the condition of the earth's surface area, fast, and spatially. The study area was in Karawang District, lying in the Northern part of West Java-Indonesia. We address a paddy growth stages classification using LANDSAT 8 image data obtained from multi-sensor remote sensing image taken in October 2015 to August 2016. This study pursues a fast and accurate classification of paddy growth stages by employing multiple regularizations learning on some deep learning methods such as DNN (Deep Neural Networks) and 1-D CNN (1-D …
University of Science and Technology of China（中国科学技术大学）
Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID is more challenging and exists a large domain gap between ImageNet classification. Inspired by the great success of self-supervised representation learning with contrastive objectives, in this paper, we design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID. During the pre-training, we attempt to address two critical issues for learning fine-grained ReID …
Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning
School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学）；School of Automation, Central South University（自动化学院，中南大学）；School of Computer Science and Technology, Beijing Jiaotong University（计算机科学与技术学院，北京交通大学）
Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
Helmholtz Pioneer Campus, Helmholtz Munich（亥姆霍兹先锋园区，亥姆霍兹慕尼黑中心）；Biozentrum, University of Basel（巴塞尔大学生物中心）；LMU University Hospital, LMU Munich（慕尼黑大学医院，慕尼黑大学）
East China Normal University（华东师范大学）；Xiamen University（厦门大学）；Tencent Youtu Lab（腾讯优图实验室）
Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing network while negative information is unexploited. Moreover, most of them focus on strengthening the dehazing network with an increase of depth and width, leading to a significant requirement of computation and memory. In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images an…
Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss that performs the prototypical regularization aggressively, e.g., the ProtoNCE loss, might cause the "coagulation" of examples in the embedding space. That is, the intra-prototype diversity of samples collapses to trivial solutions for their prototype being well-separated from others. Motivated by previous works, we propose to mitigate this phenomenon by learni…
