Recent works have advanced the performance of self-supervised representation learning by a large margin. The core among these methods is intra-image invariance learning. Two different transformations of one image instance are considered as a positive sample pair, where various tasks are designed to learn invariant representations by comparing the pair. Analogically, for video data, representations of frames from the same video are trained to be closer than frames from other videos, i.e. intra-video invariance. However, cross-video relation has barely been explored for visual representation learning. Unlike intra-video invariance, ground-truth labels of cross-video relation is usually unavailable without human labors. In this paper, we propose a novel contrastive learning method which explores the cross-video relation by using cycle-consistency for general image representation learning. This allows to collect positive sample pairs across different video instances, which we hypothesize will lead to higher-level semantics. We validate our method by transferring our image representation to multiple downstream tasks including visual object tracking, image classification, and action recognition. We show significant improvement over state-of-the-art contrastive learning methods. Project page is available at https://happywu.github.io/cycle_contrast_video.
In this paper we show that learning video feature spaces in which temporal cycles are maximally predictable benefits action classification. In particular, we propose a novel learning approach termed Cycle Encoding Prediction (CEP) that is able to effectively represent high-level spatio-temporal structure of unlabelled video content. CEP builds a latent space wherein the concept of closed forward-backward as well as backward-forward temporal loops is approximately preserved. As a self-supervision signal, CEP leverages the bi-directional temporal coherence of the video stream and applies loss fu…
Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning
Laboratory for Big Data and Decision（大数据与决策实验室）；National University of Defense Technology（国防科技大学）；Department of Information Engineering and Computer Science（信息工程与计算机科学系）
In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary supervision signal. CrosSCLR consists of both single-view contrastive learning (SkeletonCLR) and cross-view consistent knowledge mining (CVC-KM) modules, integrated in a collaborative learning manner. It is noted that CVC-KM works in such a way that high-confidence positive/negative samples and their distributions are exchanged among views according to their embedding similarity, ensuring cross-view consistency in terms…
Lumada Data Science Lab. Hitachi, Ltd.（日立有限公司卢马达数据科学实验室）
We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Following a nature that there is a belong and inclusion relation of video and its frames, CCL is designed to find correspondences across frames and videos considering the contrastive representation in their domains respectively. It is different from recent approaches that merely learn correspondences across frames or clips. In our method, the frame and video representations are learned from a single network based on an R3D architecture, with a shared non-linear transformation for embe…
Cycle Consistency in Video Object-Centric Learning
Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland（艾洛大学电气工程与自动化系，芬兰 Espoo）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China（华中科技大学人工智能与自动化学院，中国 Wuhan）；Department of Computer Science, Aalto University, Espoo, Finland（艾洛大学计算机科学系，芬兰 Espoo）；Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland（奥卢大学机器视觉与信号分析中心，芬兰 Oulu）
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）
Visual tempo, which describes how fast an action goes, has shown its potential in supervised action recognition. In this work, we demonstrate that visual tempo can also serve as a self-supervision signal for video representation learning. We propose to maximize the mutual information between representations of slow and fast videos via hierarchical contrastive learning (VTHCL). Specifically, by sampling the same instance at slow and fast frame rates respectively, we can obtain slow and fast video frames which share the same semantics but contain different visual tempos. Video representations le…
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 …
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 …
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…
Prototype Contrastive Consistency Learning for Semi-Supervised Medical Image Segmentation
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Computer Vision Institute, College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院计算机视觉研究所）；Baoan Central Hospital of Shenzhen（深圳市宝安中心医院）
3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning
School of Computer Science, Wuhan University（武汉大学计算机学院）；AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院）；Huazhong University of Science and Technology（华中科技大学）；Wuhan National Laboratory for Optoelectronics（武汉光电国家实验室）
University of Missouri（密苏里大学）；Beijing Jiaotong University（北京交通大学）
Existing approaches for unsupervised metric learning focus on exploring self-supervision information within the input image itself. We observe that, when analyzing images, human eyes often compare images against each other instead of examining images individually. In addition, they often pay attention to certain keypoints, image regions, or objects which are discriminative between image classes but highly consistent within classes. Even if the image is being transformed, the attention pattern will be consistent. Motivated by this observation, we develop a new approach to unsupervised deep metr…
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…
Robust motion forecasting of the dynamic scene is a critical component of an autonomous vehicle. It is a challenging problem due to the heterogeneity in the scene and the inherent uncertainties in the problem. To improve the accuracy of motion forecasting, in this work, we identify a new consistency constraint in this task, that is an agent's future trajectory should be coherent with its history observations and visa versa. To leverage this property, we propose a novel cycle consistency training scheme and define a novel cycle loss to encourage this consistency. In particular, we reverse the p…
Sun Yat-Sen University（中山大学）；Xidian University（西安电子科技大学）；The Sixth Affiliated Hospital, Sun Yat-sen University（中山大学附属第六医院）
Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation. According to the experience of medical imaging experts, local attributes such as texture, luster and smoothness are very important factors for identifying target objects like lesions and polyps in medical images. Motivated by this, we propose a cross-level contrastive learning scheme to enhance representation capacity for local features in semi-supervised medical image …
DI3CL: Contrastive Learning With Dynamic Instances and Contour Consistency for SAR Land-Cover Classification Foundation Model
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education（教育部智能感知与图像理解重点实验室）；International Research Center for Intelligent Perception and Computation（智能感知与计算国际研究中心）；Joint International Research Laboratory of Intelligent Perception and Computation（智能感知与计算联合国际实验室）；School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；Hangzhou Institute of Technology（杭州科技学院）
National Yang Ming Chiao Tung University（国立阳明交通大学）
Faces manifest large variations in many aspects, such as identity, expression, pose, and face styling. Therefore, it is a great challenge to disentangle and extract these characteristics from facial images, especially in an unsupervised manner. In this work, we introduce cycle-consistency in facial characteristics as free supervisory signal to learn facial representations from unlabeled facial images. The learning is realized by superimposing the facial motion cycle-consistency and identity cycle-consistency constraints. The main idea of the facial motion cycle-consistency is that, given a fac…
The University of Hong Kong（香港大学）；Tencent AI Lab（腾讯AI实验室）；ETH Zürich（苏黎世联邦理工学院）；Tencent Data Platform（腾讯数据平台）
Image virtual try-on replaces the clothes on a person image with a desired in-shop clothes image. It is challenging because the person and the in-shop clothes are unpaired. Existing methods formulate virtual try-on as either in-painting or cycle consistency. Both of these two formulations encourage the generation networks to reconstruct the input image in a self-supervised manner. However, existing methods do not differentiate clothing and non-clothing regions. A straight-forward generation impedes virtual try-on quality because of the heavily coupled image contents. In this paper, we propose …
Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and clustering objective into consideration, thus the learned representations are not optimal for clustering and the performance might be limited. Towards this issue, we first propose a novel graph contrastive learning framework, which is then applied to the clustering task and we come up with the Graph Constrastive Clustering~(GCC) method. Different from basic contrasti…
CyclePose -- Leveraging Cycle-Consistency for Annotation-Free Nuclei Segmentation in Fluorescence Microscopy
Friedrich-Alexander-Universität (FAU)（弗里德里希-亚历山大-埃尔朗根-纽伦堡大学（FAU））；Universität Würzburg（维尔茨堡大学）；Center for AI and Data Science (CAIDAS)（人工智能与数据科学中心（CAIDAS））
Video frame extrapolation is a task to predict future frames when the past frames are given. Unlike previous studies that usually have been focused on the design of modules or construction of networks, we propose a novel Extrapolative-Interpolative Cycle (EIC) loss using pre-trained frame interpolation module to improve extrapolation performance. Cycle-consistency loss has been used for stable prediction between two function spaces in many visual tasks. We formulate this cycle-consistency using two mapping functions; frame extrapolation and interpolation. Since it is easier to predict intermed…
University of Science and Technology of China（中国科学技术大学）
Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing self-supervised methods applied in natural imaging tasks focus on designing proxy tasks for unlabeled data. For example, contrastive learning is often based on the fact that an image and its transformed version share the same identity. However, pixel annotations contain much valuable information for medical image segmentation, which is largely ignored in contrastive l…
The cycleGAN is becoming an influential method in medical image synthesis. However, due to a lack of direct constraints between input and synthetic images, the cycleGAN cannot guarantee structural consistency between these two images, and such consistency is of extreme importance in medical imaging. To overcome this, we propose a structure-constrained cycleGAN for brain MR-to-CT synthesis using unpaired data that defines an extra structure-consistency loss based on the modality independent neighborhood descriptor to constrain structural consistency. Additionally, we use a position-based select…
Samsung AI Center, Cambridge（三星人工智能中心剑桥）；University of Nottingham（诺丁汉大学）
This paper addresses a major flaw of the cycle consistency loss when used to preserve the input appearance in the face-to-face synthesis domain. In particular, we show that the images generated by a network trained using this loss conceal a noise that hinders their use for further tasks. To overcome this limitation, we propose a ''recurrent cycle consistency loss" which for different sequences of target attributes minimises the distance between the output images, independent of any intermediate step. We empirically validate not only that our loss enables the re-use of generated images, but tha…
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
Mitochondria segmentation in electron microscopy images is essential in neuroscience. However, due to the image degradation during the imaging process, the large variety of mitochondrial structures, as well as the presence of noise, artifacts and other sub-cellular structures, mitochondria segmentation is very challenging. In this paper, we propose a novel and effective contrastive learning framework to learn a better feature representation from hard examples to improve segmentation. Specifically, we adopt a point sampling strategy to pick out representative pixels from hard examples in the tr…
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…
Discriminative deep learning approaches have shown impressive results for problems where human-labeled ground truth is plentiful, but what about tasks where labels are difficult or impossible to obtain? This paper tackles one such problem: establishing dense visual correspondence across different object instances. For this task, although we do not know what the ground-truth is, we know it should be consistent across instances of that category. We exploit this consistency as a supervisory signal to train a convolutional neural network to predict cross-instance correspondences between pairs of i…
We explore the task of Canonical Surface Mapping (CSM). Specifically, given an image, we learn to map pixels on the object to their corresponding locations on an abstract 3D model of the category. But how do we learn such a mapping? A supervised approach would require extensive manual labeling which is not scalable beyond a few hand-picked categories. Our key insight is that the CSM task (pixel to 3D), when combined with 3D projection (3D to pixel), completes a cycle. Hence, we can exploit a geometric cycle consistency loss, thereby allowing us to forgo the dense manual supervision. Our approa…
Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness. Such models typically require joint reasoning in the image and text representation spaces for downstream inference tasks. Contrary to prior beliefs, we demonstrate that the image and text representations learned via a standard contrastive objective are not interchangeable and can lead to inconsistent downstream predictions. To mitigate this issue, we formalize consistency and prop…
Learning to synthesize high frame rate videos via interpolation requires large quantities of high frame rate training videos, which, however, are scarce, especially at high resolutions. Here, we propose unsupervised techniques to synthesize high frame rate videos directly from low frame rate videos using cycle consistency. For a triplet of consecutive frames, we optimize models to minimize the discrepancy between the center frame and its cycle reconstruction, obtained by interpolating back from interpolated intermediate frames. This simple unsupervised constraint alone achieves results compara…
University of Oxford（牛津大学）；University of Texas（德克萨斯大学）；Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Previous cycle-consistency correspondence learning methods usually leverage image patches for training. In this paper, we present a fully convolutional method, which is simpler and more coherent to the inference process. While directly applying fully convolutional training results in model collapse, we study the underline reason behind this collapse phenomenon, indicating that the absolute positions of pixels provide a shortcut to easily accomplish cycle-consistence, which hinders the learning of meaningful visual representations. To break this absolute position shortcut, we propose to apply d…
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 …
University of Bonn（波恩大学）；The University of Melbourne（墨尔本大学）；MPI Informatics（马克斯·普朗克信息学研究所）
With the success of deep learning methods in analyzing activities in videos, more attention has recently been focused towards anticipating future activities. However, most of the work on anticipation either analyzes a partially observed activity or predicts the next action class. Recently, new approaches have been proposed to extend the prediction horizon up to several minutes in the future and that anticipate a sequence of future activities including their durations. While these works decouple the semantic interpretation of the observed sequence from the anticipation task, we propose a framew…
We introduce a weakly supervised method for representation learning based on aligning temporal sequences (e.g., videos) of the same process (e.g., human action). The main idea is to use the global temporal ordering of latent correspondences across sequence pairs as a supervisory signal. In particular, we propose a loss based on scoring the optimal sequence alignment to train an embedding network. Our loss is based on a novel probabilistic path finding view of dynamic time warping (DTW) that contains the following three key features: (i) the local path routing decisions are contrastive and diff…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Osaka University（大阪大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
CT is commonly used in orthopedic procedures. MRI is used along with CT to identify muscle structures and diagnose osteonecrosis due to its superior soft tissue contrast. However, MRI has poor contrast for bone structures. Clearly, it would be helpful if a corresponding CT were available, as bone boundaries are more clearly seen and CT has standardized (i.e., Hounsfield) units. Therefore, we aim at MR-to-CT synthesis. The CycleGAN was successfully applied to unpaired CT and MR images of the head, these images do not have as much variation of intensity pairs as do images in the pelvic region du…
Computer Vision Center（计算机视觉中心）；Autonomous University of Barcelona（巴塞罗那自治大学）；Amsterdam Machine Learning Lab（阿姆斯特丹机器学习实验室）；University of Amsterdam（阿姆斯特丹大学）
Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase. Existing works either require aligned sketch-image pairs or inefficient memory fusion layer for mapping the visual information to a semantic space. In this work, we propose a semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maps the visual information to a common semantic space via an adversarial training. Each of these branches maintains …
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 …
