Orientation estimation is the core to a variety of vision and robotics tasks such as camera and object pose estimation. Deep learning has offered a way to develop image-based orientation estimators; however, such estimators often require training on a large labeled dataset, which can be time-intensive to collect. In this work, we explore whether self-supervised learning from unlabeled data can be used to alleviate this issue. Specifically, we assume access to estimates of the relative orientation between neighboring poses, such that can be obtained via a local alignment method. While self-supervised learning has been used successfully for translational object keypoints, in this work, we show that naively applying relative supervision to the rotational group $SO(3)$ will often fail to converge due to the non-convexity of the rotational space. To tackle this challenge, we propose a new algorithm for self-supervised orientation estimation which utilizes Modified Rodrigues Parameters to stereographically project the closed manifold of $SO(3)$ to the open manifold of $\mathbb{R}^{3}$, allowing the optimization to be done in an open Euclidean space. We empirically validate the benefits of the proposed algorithm for rotational averaging problem in two settings: (1) direct optimization on rotation parameters, and (2) optimization of parameters of a convolutional neural network that predicts object orientations from images. In both settings, we demonstrate that our proposed algorithm is able to converge to a consistent relative orientation frame much faster than algorithms that purely operate in the $SO(3)$ space. Additional information can be found at https://sites.google.com/view/deep-projective-rotation/home .
Peking University（北京大学）；Beijing Institute for General AI（北京通用人工智能研究院）；Stanford University（斯坦福大学）；Imperial College London（伦敦帝国理工学院）
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several works have proposed different regression-friendly rotation representations, very few works have been devoted to improving the gradient backpropagating in the backward pass. In this paper, we propose a manifold-aware gradient that directly backpropagates into deep network weights. Leveraging Riemannian…
Recently, it is shown that deploying a proper self-supervision is a prospective way to enhance the performance of supervised learning. Yet, the benefits of self-supervision are not fully exploited as previous pretext tasks are specialized for unsupervised representation learning. To this end, we begin by presenting three desirable properties for such auxiliary tasks to assist the supervised objective. First, the tasks need to guide the model to learn rich features. Second, the transformations involved in the self-supervision should not significantly alter the training distribution. Third, the …
Image captioning is a task in the field of Artificial Intelligence that merges between computer vision and natural language processing. It is responsible for generating legends that describe images, and has various applications like descriptions used by assistive technology or indexing images (for search engines for instance). This makes it a crucial topic in AI that is undergoing a lot of research. This task however, like many others, is trained on large images labeled via human annotation, which can be very cumbersome: it needs manual effort, both financial and temporal costs, it is error-pr…
Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typically addressed by matching local descriptors. Recently, a few attempts at applying the deep learning paradigm to the task have shown promising results. Yet, the only explored way to learn rotation invariant descriptors has been to feed neural networks with highly engineered and invariant representations provided by existing hand-crafted descriptors, a path that goes in the opposite direction of end-to-end learning from raw data so successfully deployed for 2D images. In this paper, we explore the b…
University of Washington (UW)（华盛顿大学）；Rochester Institute of Technology（罗切斯特理工学院）
Accurate and real-time surgical instrument segmentation is important in the endoscopic vision of robot-assisted surgery, and significant challenges are posed by frequent instrument-tissue contacts and continuous change of observation perspective. For these challenging tasks more and more deep neural networks (DNN) models are designed in recent years. We are motivated to propose a general embeddable approach to improve these current DNN segmentation models without increasing the model parameter number. Firstly, observing the limited rotation-invariance performance of DNN, we proposed the Multi-…
Brown University（布朗大学）；University of Maryland（马里兰大学）；Facebook AI（脸书人工智能研究院）
Deep metric learning is an important area due to its applicability to many domains such as image retrieval and person re-identification. The main drawback of such models is the necessity for labeled data. In this work, we propose to generate pseudo-labels for deep metric learning directly from clustering assignment and we introduce unsupervised deep metric learning (UDML) regularized by a self-supervision (SS) task. In particular, we propose to regularize the training process by predicting image rotations. Our method (UDML-SS) jointly learns discriminative embeddings, unsupervised clustering a…
VoxelCloud, Inc.（体素云公司）；Second Military Medical University（第二军医大学）；Changzheng Hospital（长征医院）；Shanghai Jiaotong University School of Medicine（上海交通大学医学院）；Ruijin Hospital（瑞金医院）
We investigate the effectiveness of a simple solution to the common problem of deep learning in medical image analysis with limited quantities of labeled training data. The underlying idea is to assign artificial labels to abundantly available unlabeled medical images and, through a process known as surrogate supervision, pre-train a deep neural network model for the target medical image analysis task lacking sufficient labeled training data. In particular, we employ 3 surrogate supervision schemes, namely rotation, reconstruction, and colorization, in 4 different medical imaging applications …
Huazhong University of Science and Technology（华中科技大学）；Qingdao University（青岛大学）
Detecting oriented objects along with estimating their rotation information is one crucial step for analyzing remote sensing images. Despite that many methods proposed recently have achieved remarkable performance, most of them directly learn to predict object directions under the supervision of only one (e.g. the rotation angle) or a few (e.g. several coordinates) groundtruth values individually. Oriented object detection would be more accurate and robust if extra constraints, with respect to proposal and rotation information regression, are adopted for joint supervision during training. To t…
Federal Research Center “Computer Science and Control” of Russian Academy of Sciences（俄罗斯科学院“计算机科学与控制”联邦研究中心）；Moscow Institute of Physics and Technology (State University)（莫斯科物理技术学院（国立大学））；The Institute for Information Transmission Problems of Russian Academy of Sciences（俄罗斯科学院信息传输问题研究所）；Smart Engines Service LLC（Smart Engines服务有限责任公司）
This paper presents a method for metric rectification of planar objects that preserves angles and length ratios. An inner structure of an object is assumed to follow the laws of Manhattan World i.e. the majority of line segments are aligned with two orthogonal directions of the object. For that purpose we introduce the method that estimates the position of two vanishing points corresponding to the main object directions. It is based on an original optimization function of segments that estimates a vanishing point position. For calculation of the rectification homography with two vanishing poin…
Google Research（谷歌研究院）；Inria（法国国家信息与自动化研究所）；Carnegie Mellon University（卡内基梅隆大学）
We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations. Given a sequence of frames, SfM-Net predicts depth, segmentation, camera and rigid object motions, converts those into a dense frame-to-frame motion field (optical flow), differentiably warps frames in time to match pixels and back-propagates. The model can be trained with various degrees of supervision: 1) self-supervised by the re-projection photometric error (completely unsu…
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Princeton University（普林斯顿大学）；Simon Fraser University（西蒙菲莎大学）；Beijing Normal University（北京师范大学）
Hand detection is essential for many hand related tasks, e.g. parsing hand pose, understanding gesture, which are extremely useful for robotics and human-computer interaction. However, hand detection in uncontrolled environments is challenging due to the flexibility of wrist joint and cluttered background. We propose a deep learning based approach which detects hands and calibrates in-plane rotation under supervision at the same time. To guarantee the recall, we propose a context aware proposal generation algorithm which significantly outperforms the selective search. We then design a convolut…
Generative Adversarial Networks (GANs) have become the most used networks towards solving the problem of image generation. Self-supervised GANs are later proposed to avoid the catastrophic forgetting of the discriminator and to improve the image generation quality without needing the class labels. However, the generalizability of the self-supervision tasks on different GAN architectures is not studied before. To that end, we extensively analyze the contribution of a previously proposed self-supervision task, deshuffling of the DeshuffleGANs in the generalizability context. We assign the deshuf…
In this paper we publish the largest identity-annotated Holstein-Friesian cattle dataset Cows2021 and a first self-supervision framework for video identification of individual animals. The dataset contains 10,402 RGB images with labels for localisation and identity as well as 301 videos from the same herd. The data shows top-down in-barn imagery, which captures the breed's individually distinctive black and white coat pattern. Motivated by the labelling burden involved in constructing visual cattle identification systems, we propose exploiting the temporal coat pattern appearance across videos…
University of California, Los Angeles（加州大学洛杉矶分校）；Google Brain（谷歌大脑）
Conditional GANs are at the forefront of natural image synthesis. The main drawback of such models is the necessity for labeled data. In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, and take a step towards bridging the gap between conditional and unconditional GANs. In particular, we allow the networks to collaborate on the task of representation learning, while being adversarial with respect to the classic GAN game. The role of self-supervision is to encourage the discriminator to learn meaningful feature representations which a…
Automatic lesion segmentation in dermoscopy images is an essential step for computer-aided diagnosis of melanoma. The dermoscopy images exhibits rotational and reflectional symmetry, however, this geometric property has not been encoded in the state-of-the-art convolutional neural networks based skin lesion segmentation methods. In this paper, we present a deeply supervised rotation equivariant network for skin lesion segmentation by extending the recent group rotation equivariant network~\cite{cohen2016group}. Specifically, we propose the G-upsampling and G-projection operations to adapt the …
We propose the first qualitative hypothesis characterizing the behavior of visual transformation based self-supervision, called the VTSS hypothesis. Given a dataset upon which a self-supervised task is performed while predicting instantiations of a transformation, the hypothesis states that if the predicted instantiations of the transformations are already present in the dataset, then the representation learned will be less useful. The hypothesis was derived by observing a key constraint in the application of self-supervision using a particular transformation. This constraint, which we term th…
Estimating the 3DoF rotation from a single RGB image is an important yet challenging problem. Recent works achieve good performance relying on a large amount of expensive-to-obtain labeled data. To reduce the amount of supervision, we for the first time propose a general framework, FisherMatch, for semi-supervised rotation regression, without assuming any domain-specific knowledge or paired data. Inspired by the popular semi-supervised approach, FixMatch, we propose to leverage pseudo label filtering to facilitate the information flow from labeled data to unlabeled data in a teacher-student mu…
Successful applications of deep learning (DL) requires large amount of annotated data. This often restricts the benefits of employing DL to businesses and individuals with large budgets for data-collection and computation. Summarization offers a possible solution by creating much smaller representative datasets that can allow real-time deep learning and analysis of big data and thus democratize use of DL. In the proposed work, our aim is to explore a novel approach to task-specific image corpus summarization using semantic information and self-supervision. Our method uses a classification-base…
University of Pennsylvania（宾夕法尼亚大学）；Google Research（谷歌研究院）
Spherical convolutional networks have been introduced recently as tools to learn powerful feature representations of 3D shapes. Spherical CNNs are equivariant to 3D rotations making them ideally suited to applications where 3D data may be observed in arbitrary orientations. In this paper we learn 2D image embeddings with a similar equivariant structure: embedding the image of a 3D object should commute with rotations of the object. We introduce a cross-domain embedding from 2D images into a spherical CNN latent space. This embedding encodes images with 3D shape properties and is equivariant to…
Single image pose estimation is a fundamental problem in many vision and robotics tasks, and existing deep learning approaches suffer by not completely modeling and handling: i) uncertainty about the predictions, and ii) symmetric objects with multiple (sometimes infinite) correct poses. To this end, we introduce a method to estimate arbitrary, non-parametric distributions on SO(3). Our key idea is to represent the distributions implicitly, with a neural network that estimates the probability given the input image and a candidate pose. Grid sampling or gradient ascent can be used to find the m…
Rotation Augmented Distillation for Exemplar-Free Class Incremental Learning with Detailed Analysis
School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling. Leveraging auxiliary tasks such as rotation prediction or generative colorization, SSL can produce better and more robust representations in a low data regime. Training such tasks along an I2IT task is however computationally intractable as model size and the number of task grow. On the other hand, learning sequentially could incur catastrophic forgetting of previously learned tasks. To alleviate this, we intr…
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, return…
TU Wien（维也纳工业大学）；Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利理工学院）
Unsupervised Domain Adaptation (DA) exploits the supervision of a label-rich source dataset to make predictions on an unlabeled target dataset by aligning the two data distributions. In robotics, DA is used to take advantage of automatically generated synthetic data, that come with "free" annotation, to make effective predictions on real data. However, existing DA methods are not designed to cope with the multi-modal nature of RGB-D data, which are widely used in robotic vision. We propose a novel RGB-D DA method that reduces the synthetic-to-real domain shift by exploiting the inter-modal rel…
Simons Machine Learning Center（西蒙斯机器学习中心）；New York Structural Biology Center（纽约结构生物学中心）
In many imaging modalities, objects of interest can occur in a variety of locations and poses (i.e. are subject to translations and rotations in 2d or 3d), but the location and pose of an object does not change its semantics (i.e. the object's essence). That is, the specific location and rotation of an airplane in satellite imagery, or the 3d rotation of a chair in a natural image, or the rotation of a particle in a cryo-electron micrograph, do not change the intrinsic nature of those objects. Here, we consider the problem of learning semantic representations of objects that are invariant to p…
Shanghai Jiao Tong University（上海交通大学）；Northwestern Polytechnical University（西北工业大学）；Australian National University（澳大利亚国立大学）
Contemporary deep learning multi-scale deblurring models suffer from many issues: 1) They perform poorly on non-uniformly blurred images/videos; 2) Simply increasing the model depth with finer-scale levels cannot improve deblurring; 3) Individual RGB frames contain a limited motion information for deblurring; 4) Previous models have a limited robustness to spatial transformations and noise. Below, we extend the DMPHN model by several mechanisms to address the above issues: I) We present a novel self-supervised event-guided deep hierarchical Multi-patch Network (MPN) to deal with blurry images …
Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision
Shanghai AI Laboratory（上海人工智能实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）；Southeast University（东南大学）
Microsoft Ads（微软广告）；Microsoft AI & Research（微软人工智能与研究院）
Contextual bandits are a common problem faced by machine learning practitioners in domains as diverse as hypothesis testing to product recommendations. There have been a lot of approaches in exploiting rich data representations for contextual bandit problems with varying degree of success. Self-supervised learning is a promising approach to find rich data representations without explicit labels. In a typical self-supervised learning scheme, the primary task is defined by the problem objective (e.g. clustering, classification, embedding generation etc.) and the secondary task is defined by the …
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work, we propose a generic method for self-supervised domain adaptation, using object recognition and semantic segmentation of urban scenes as use cases. Focusing on simple pretext/auxiliary tasks (e.g. image rotation prediction), we assess different learning strategies to improve domain adaptation effectiveness by self-supervision. Additionally, we pro…
Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly and time-consuming to collect. In this paper, we leverage 3D self-supervision for learning downstream tasks on point clouds with fewer labels. A point cloud can be rotated in infinitely many ways, which provides a rich label-free source for self-supervision. We consider the auxiliary task of predicting rotations that in turn leads to useful features for othe…
Mila（米拉研究所）；Universite de Montreal（蒙特利尔大学）；Brown University（布朗大学）；Robotics Research Center, KCIS, International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院KCIS机器人研究中心）
We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images. Canonical shape reconstruction, estimating 3D object shape in a coordinate space canonicalized for scale, rotation, and translation parameters, is an emerging paradigm that holds promise for a multitude of robotic applications. Prior approaches either rely on painstakingly gathered dense 3D supervision, or produce only sparse canonical representations, limiting real-world applicability. DRACO performs dense canonicalization using only weak supervision in the form of camera pose…
Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-the-wild shapes, eg., from internet model collections or depth sensors. ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds. We build on top of Tensor Field Networks (TFNs), a class of permutation- and rotation-equivariant, and translation-invariant 3D networks. During inference, our method takes an …
