Unlabeled data learning has attracted considerable attention recently. However, it is still elusive to extract the expected high-level semantic feature with mere unsupervised learning. In the meantime, semi-supervised learning (SSL) demonstrates a promising future in leveraging few samples. In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating. Specifically, unsupervised semantic aggregation based on Triplet Mutual Information (T-MI) loss is explored to generate semantic labels for unlabeled data. Then the semantic labels are aligned to the actual class by the supervision of labeled data. Furthermore, a feature pool that stores the labeled samples is dynamically updated to assign proxy labels for unlabeled data, which are used as targets for cross-entropy minimization. Extensive experiments and analysis across four standard semi-supervised learning benchmarks validate that USADTM achieves top performance (e.g., 90.46$\%$ accuracy on CIFAR-10 with 40 labels and 95.20$\%$ accuracy with 250 labels). The code is released at https://github.com/taohan10200/USADTM.
A novel template matching algorithm that can incorporate the concept of deformable parts, is presented in this paper. Unlike the deformable part model (DPM) employed in object recognition, the proposed template-matching approach called Deformable Template Matching (DTM) does not require a training step. Instead, deformation is achieved by a set of predefined basic rules (e.g. the left sub-patch cannot pass across the right patch). Experimental evaluation of this new method using the PASCAL VOC 07 dataset demonstrated substantial performance improvement over conventional template matching algor…
Deformable templates are essential to large-scale medical image registration, segmentation, and population analysis. Current conventional and deep network-based methods for template construction use only regularized registration objectives and often yield templates with blurry and/or anatomically implausible appearance, confounding downstream biomedical interpretation. We reformulate deformable registration and conditional template estimation as an adversarial game wherein we encourage realism in the moved templates with a generative adversarial registration framework conditioned on flexible i…
We propose a novel measure for template matching named Deformable Diversity Similarity -- based on the diversity of feature matches between a target image window and the template. We rely on both local appearance and geometric information that jointly lead to a powerful approach for matching. Our key contribution is a similarity measure, that is robust to complex deformations, significant background clutter, and occlusions. Empirical evaluation on the most up-to-date benchmark shows that our method outperforms the current state-of-the-art in its detection accuracy while improving computational…
We develop a learning framework for building deformable templates, which play a fundamental role in many image analysis and computational anatomy tasks. Conventional methods for template creation and image alignment to the template have undergone decades of rich technical development. In these frameworks, templates are constructed using an iterative process of template estimation and alignment, which is often computationally very expensive. Due in part to this shortcoming, most methods compute a single template for the entire population of images, or a few templates for specific sub-groups of …
School of Electrical & Information Engineering, University of the Witwatersrand（威特沃特斯兰德大学电气与信息工程学院）
This paper presents deformable templates as a tool for segmentation and localization of biological structures in medical images. Structures are represented by a prototype template, combined with a parametric warp mapping used to deform the original shape. The localization procedure is achieved using a multi-stage, multi-resolution algorithm de-signed to reduce computational complexity and time. The algorithm initially identifies regions in the image most likely to contain the desired objects and then examines these regions at progressively increasing resolutions. The final stage of the algorit…
Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and the features of the target template and search image are computed independently in a Siamese architecture. In this paper, we propose Deformable Siamese Attention Networks, referred to as SiamAttn, by introducing a new Siamese attention mechanism that computes deformable self-attention and cross-attention. The self attention learns strong context information via spatial attention, and selectively emphasizes interdependent channel-wise features with channe…
Imperial College London（帝国理工学院）；TheraPanacea；University of Oxford（牛津大学）；CentraleSupelec（中央高等电力学院）；INRIA（法国国家信息与自动化研究所）；Universite Paris-Saclay（巴黎萨克雷大学）
We propose a novel weakly supervised discriminative algorithm for learning context specific registration metrics as a linear combination of conventional similarity measures. Conventional metrics have been extensively used over the past two decades and therefore both their strengths and limitations are known. The challenge is to find the optimal relative weighting (or parameters) of different metrics forming the similarity measure of the registration algorithm. Hand-tuning these parameters would result in sub optimal solutions and quickly become infeasible as the number of metrics increases. Fu…
Learning deformable 3D objects from 2D images is often an ill-posed problem. Existing methods rely on explicit supervision to establish multi-view correspondences, such as template shape models and keypoint annotations, which restricts their applicability on objects "in the wild". A more natural way of establishing correspondences is by watching videos of objects moving around. In this paper, we present DOVE, a method that learns textured 3D models of deformable object categories from monocular videos available online, without keypoint, viewpoint or template shape supervision. By resolving sym…
Technical University of Munich（慕尼黑工业大学）；University of Melbourne（墨尔本大学）；German Aerospace Center（德国航空航天中心）
Training semantic segmentation models with few annotated samples has great potential in various real-world applications. For the few-shot segmentation task, the main challenge is how to accurately measure the semantic correspondence between the support and query samples with limited training data. To address this problem, we propose to aggregate the learnable covariance matrices with a deformable 4D Transformer to effectively predict the segmentation map. Specifically, in this work, we first devise a novel hard example mining mechanism to learn covariance kernels for the Gaussian process. The …
Instituto de Investigación en Ingeniería de Aragón (I3A), Universidad de Zaragoza（萨拉戈萨大学阿拉贡工程研究所（I3A））
Deformable Monocular SLAM algorithms recover the localization of a camera in an unknown deformable environment. Current approaches use a template-based deformable tracking to recover the camera pose and the deformation of the map. These template-based methods use an underlying global deformation model. In this paper, we introduce a novel deformable camera tracking method with a local deformation model for each point. Each map point is defined as a single textured surfel that moves independently of the other map points. Thanks to a direct photometric error cost function, we can track the positi…
Research institute for signals, systems and computational intelligence, sinc(i), FICH-UNL/CONICET（信号、系统与计算智能研究所 sinc(i)，FICH-UNL/CONICET）；University of Oxford（牛津大学）；TheraPanacea；CentraleSupelec（中央理工-高等电力学院）；Universite Paris-Saclay（巴黎-萨克雷大学）
Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with a deformation model and a smoothness constraint, determines the optimal transformation to align two given images. The definition of this metric function is among the most critical aspects of the registration process. We argue that incorporating semantic information (in the form of anatomical segmentation maps) into the registration process will further improve the accuracy of the results. In this paper, we propose a…
Universidad de Alcalá（阿尔卡拉大学）；Universidad Rey Juan Carlos（胡安卡洛斯国王大学）；Institut de Recherche contre les Cancers de l’Appareil Digestif（消化道癌症研究所）；Université Clermont-Auvergne（克莱蒙奥弗涅大学）
We present Deep Shape-from-Template (DeepSfT), a novel Deep Neural Network (DNN) method for solving real-time automatic registration and 3D reconstruction of a deformable object viewed in a single monocular image.DeepSfT advances the state-of-the-art in various aspects. Compared to existing DNN SfT methods, it is the first fully convolutional real-time approach that handles an arbitrary object geometry, topology and surface representation. It also does not require ground truth registration with real data and scales well to very complex object models with large numbers of elements. Compared to …
Deformable surface tracking from monocular images is well-known to be under-constrained. Occlusions often make the task even more challenging, and can result in failure if the surface is not sufficiently textured. In this work, we explicitly address the problem of 3D reconstruction of poorly textured, occluded surfaces, proposing a framework based on a template-matching approach that scales dense robust features by a relevancy score. Our approach is extensively compared to current methods employing both local feature matching and dense template alignment. We test on standard datasets as well a…
Tianjin University（天津大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；University of Science and Technology of China（中国科学技术大学）；Automotive Data of China (Tianjin) Co., Ltd（中国汽车技术研究中心有限公司）
Recently, template-based trackers have become the leading tracking algorithms with promising performance in terms of efficiency and accuracy. However, the correlation operation between query feature and the given template only exploits accurate target localization, leading to state estimation error especially when the target suffers from severe deformable variations. To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively. However, most of existing trackers only refer to the targe…
A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Tianjin University（天津大学）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所）；Linköping University（林雪平大学）
University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology（哈尔滨工业大学）；SenseTime Research（商汤科技研究院）
Point clouds and RGB images are two general perceptional sources in autonomous driving. The former can provide accurate localization of objects, and the latter is denser and richer in semantic information. Recently, AutoAlign presents a learnable paradigm in combining these two modalities for 3D object detection. However, it suffers from high computational cost introduced by the global-wise attention. To solve the problem, we propose Cross-Domain DeformCAFA module in this work. It attends to sparse learnable sampling points for cross-modal relational modeling, which enhances the tolerance to c…
We provide a novel new approach for aligning geometric models using a dual graph structure where local features are mapping probabilities. Alignment of non-rigid structures is one of the most challenging computer vision tasks due to the high number of unknowns needed to model the correspondence. We have seen a leap forward using DNN models in template alignment and functional maps, but those methods fail for inter-class alignment where nonisometric deformations exist. Here we propose to rethink this task and use unrolling concepts on a dual graph structure - one for a forward map and one for a…
The Hong Kong University of Science and Technology（香港科技大学）；Tencent（腾讯）
Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking, significantly much more research effort has been made in segmentation than tracking. In this paper, we introduce "tracking-by-detection" into VOS which can coherently integrate segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. Notably, …
Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Mechanical Engineering and Automation, Harbin Institute of Technology at Shenzhen（哈尔滨工业大学（深圳）机械工程与自动化学院）
Template-Based Feature Aggregation Network for Industrial Anomaly Detection
State Key Laboratory of Precision Measurement Technology and Instruments（精密测量技术与仪器国家重点实验室）；Tsinghua University（清华大学）；State Key Laboratory of Digital Manufacturing Equipment and Technology（数字制造装备与技术国家重点实验室）；Huazhong University of Science and Technology（华中科技大学）
Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings
Nanyang Technological University（南洋理工大学）；Peking University（北京大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；SenseTime Research（商汤科技研究院）
In general, the problem of non-rigid registration is about matching two different scans of a dynamic object taken at two different points in time. These scans can undergo both rigid motions and non-rigid deformations. Since new parts of the model may come into view and other parts get occluded in between two scans, the region of overlap is a subset of both scans. In the most general setting, no prior template shape is given and no markers or explicit feature point correspondences are available. So, this case is a partial matching problem that takes into account the assumption that consequent s…
More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing or resisting to drift. This paper proposes a correlation filter based tracking method which aggregates historical features in a spatial-aligned and scale-aware paradigm. The features of historical frames are sampled and aggregated to search frame according to a pixel-level alignment module based on deformable convolutions. In addition, we also use a feature …
Universität Siegen（锡根大学）；Sapienza Università di Roma（罗马大学）；Università della Svizzera Italiana（提契诺大学）；Technische Universität München（慕尼黑工业大学）
We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D shape represented as a planar curve and a 3D shape represented as a surface; the output is a continuous curve on the surface. We cast the problem as finding the shortest circular path on the product 3-manifold of the surface and the curve. We prove that the optimal matching can be computed in polynomial time with a (worst-case) complexity of $O(mn^2\log(n))$, where $m$ and $n$ denote the number of vertices on the template curve and the 3D shape respectively. We also demonstrate that in practice the ru…
Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images. Recently, RefSR has been attracting great attention as it provides an alternative way to surpass single image SR. However, addressing the RefSR problem has two critical challenges: (i) It is difficult to match the correspondence between LR and Ref images when they are significantly different; (ii) How to transfer the relevant texture from Ref images to compensate the details for LR images is very challenging. To address these issues of RefSR, this paper p…
Video object detection is a fundamental yet challenging task in computer vision. One practical solution is to take advantage of temporal information from the video and apply feature aggregation to enhance the object features in each frame. Though effective, those existing methods always suffer from low inference speeds because they use a fixed number of frames for feature aggregation regardless of the input frame. Therefore, this paper aims to improve the inference speed of the current feature aggregation-based video object detectors while maintaining their performance. To achieve this goal, w…
In most computer vision and image analysis problems, it is necessary to define a similarity measure between two or more different objects or images. Template matching is a classic and fundamental method used to score similarities between objects using certain mathematical algorithms. In this paper, we reviewed the basic concept of matching, as well as advances in template matching and applications such as invariant features or novel applications in medical image analysis. Additionally, deformable models and templates originating from classic template matching were discussed. These models have …
Generalizing Shape-from-Template to Topological Changes
Università degli Studi di Padova（帕多瓦大学）；University of California, Berkeley（加州大学伯克利分校）；Freie Universität Berlin（柏林自由大学）；Technische Universität Berlin（柏林工业大学）；Zuse Institute Berlin（柏林楚泽研究所）
University of Verona（维罗纳大学）；Sapienza University of Rome（罗马萨皮恩扎大学）
We propose a new approach for 3D shape matching of deformable human shapes. Our approach is based on the joint adoption of three different tools: an intrinsic spectral matching pipeline, a morphable model, and an extrinsic details refinement. By operating in conjunction, these tools allow us to greatly improve the quality of the matching while at the same time resolving the key issues exhibited by each tool individually. In this paper we present an innovative High-Resolution Augmentation (HRA) strategy that enables highly accurate correspondence even in the presence of significant mesh resolut…
Stony Brook University（石溪大学）；CentraleSupélec（高等电力学院）；INRIA（法国国家信息与自动化研究所）；Therapanacea；University College London（伦敦大学学院）；Facebook AI Research（Facebook人工智能研究院）
In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (`template') and an observed image, while appearance is modeled in `canonical', template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise image alignment. W…
LIGM (UMR 8049), École des Ponts, UPE（LIGM（UMR 8049），桥路学院，巴黎东大）；Adobe Research（Adobe研究院）
We present a new deep learning approach for matching deformable shapes by introducing {\it Shape Deformation Networks} which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a template, that parameterizes the surface, and (ii) a learnt global feature vector that parameterizes the transformation of the template into the input surface. By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template. We show that these correspondences can be improved by an additional step which imp…
3D object detection using point clouds has attracted increasing attention due to its wide applications in autonomous driving and robotics. However, most existing studies focus on single point cloud frames without harnessing the temporal information in point cloud sequences. In this paper, we design TransPillars, a novel transformer-based feature aggregation technique that exploits temporal features of consecutive point cloud frames for multi-frame 3D object detection. TransPillars aggregates spatial-temporal point cloud features from two perspectives. First, it fuses voxel-level features direc…
Nanjing University of Science and Technology（南京理工大学）
Learning robust feature matching between the template and search area is crucial for 3D Siamese tracking. The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization. In this paper, we propose a novel point cloud registration-driven Siamese tracking framework, with the intuition that spatially aligned corresponding points (via 3D registration) tend to achieve consistent feature representations. Specifically, our method consists of two modules, including a tracking-specific nonloca…
Twin Deformable Point Convolutions for Point Cloud Semantic Segmentation in Remote Sensing Scenes
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Tsinghua University（清华大学）；Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
Huazhong University of Science and Technology（华中科技大学）；La Trobe University（拉筹伯大学）
Transformer framework has been showing superior performances in visual object tracking for its great strength in information aggregation across the template and search image with the well-known attention mechanism. Most recent advances focus on exploring attention mechanism variants for better information aggregation. We find these schemes are equivalent to or even just a subset of the basic self-attention mechanism. In this paper, we prove that the vanilla self-attention structure is sufficient for information aggregation, and structural adaption is unnecessary. The key is not the attention s…
University of California, Merced（加州大学默塞德分校）；NVIDIA（英伟达）
We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not necessitate 3D supervision, manually annotated keypoints, multi-view images of an object or a prior 3D template. The key insight of our work is that objects can be represented as a collection of deformable parts, and each part is semantically coherent across different instances of the same category (e.g., wings on birds and wheels on cars). Therefore, by leveraging self-supervised…
