PyTorchKR Papers

최신 논문

총 9,714편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2111.08383

Single Image Object Counting and Localizing using Active-Learning

The need to count and localize repeating objects in an image arises in different scenarios, such as biological microscopy studies, production lines inspection, and surveillance recordings analysis. The use of supervised Convoutional Neural Networks (CNNs) achieves accurate object detection when trained over large class-specific datasets. The labeling effort in this approach does not pay-off when the counting is required over few images of a unique object class. We present a new method for counting and localizing repeating objects in single-image scenarios, assuming no pre-trained classifier is available. Our method trains a CNN over a small set of labels carefully collected from the input image in few active-learning iterations. At each iteration, the latent space of the network is analyzed to extract a minimal number of user-queries that strives to both sample the in-class manifold as thoroughly as possible as well as avoid redundant labels. Compared with existing user-assisted counting methods, our active-learning iterations achieve state-of-the-art performance in terms of counting and localizing accuracy, number of user mouse clicks, and running-time. This evaluation was performed through a large user study over a wide range of image classes with diverse conditions of illumination and occlusions.

arXiv:2111.08276공식 코드 · Papers with Code

Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts

Most existing methods in vision language pre-training rely on object-centric features extracted through object detection and make fine-grained alignments between the extracted features and texts. It is challenging for these methods to learn relations among multiple objects. To this end, we propose a new method called X-VLM to perform `multi-grained vision language pre-training.' The key to learning multi-grained alignments is to locate visual concepts in the image given the associated texts, and in the meantime align the texts with the visual concepts, where the alignments are in multi-granularity. Experimental results show that X-VLM effectively leverages the learned multi-grained alignments to many downstream vision language tasks and consistently outperforms state-of-the-art methods.

arXiv:2111.08174

ShapeY: Measuring Shape Recognition Capacity Using Nearest Neighbor Matching

Object recognition in humans depends primarily on shape cues. We have developed a new approach to measuring the shape recognition performance of a vision system based on nearest neighbor view matching within the system's embedding space. Our performance benchmark, ShapeY, allows for precise control of task difficulty, by enforcing that view matching span a specified degree of 3D viewpoint change and/or appearance change. As a first test case we measured the performance of ResNet50 pre-trained on ImageNet. Matching error rates were high. For example, a 27 degree change in object pitch led ResNet50 to match the incorrect object 45% of the time. Appearance changes were also highly disruptive. Examination of false matches indicates that ResNet50's embedding space is severely "tangled". These findings suggest ShapeY can be a useful tool for charting the progress of artificial vision systems towards human-level shape recognition capabilities.

arXiv:2111.07447

Learning Multi-Stage Tasks with One Demonstration via Self-Replay

In this work, we introduce a novel method to learn everyday-like multi-stage tasks from a single human demonstration, without requiring any prior object knowledge. Inspired by the recent Coarse-to-Fine Imitation Learning method, we model imitation learning as a learned object reaching phase followed by an open-loop replay of the demonstrator's actions. We build upon this for multi-stage tasks where, following the human demonstration, the robot can autonomously collect image data for the entire multi-stage task, by reaching the next object in the sequence and then replaying the demonstration, and then repeating in a loop for all stages of the task. We evaluate with real-world experiments on a set of everyday-like multi-stage tasks, which we show that our method can solve from a single demonstration. Videos and supplementary material can be found at https://www.robot-learning.uk/self-replay.

arXiv:2111.07072

Factorial Convolution Neural Networks

In recent years, GoogleNet has garnered substantial attention as one of the base convolutional neural networks (CNNs) to extract visual features for object detection. However, it experiences challenges of contaminated deep features when concatenating elements with different properties. Also, since GoogleNet is not an entirely lightweight CNN, it still has many execution overheads to apply to a resource-starved application domain. Therefore, a new CNNs, FactorNet, has been proposed to overcome these functional challenges. The FactorNet CNN is composed of multiple independent sub CNNs to encode different aspects of the deep visual features and has far fewer execution overheads in terms of weight parameters and floating-point operations. Incorporating FactorNet into the Faster-RCNN framework proved that FactorNet gives \ignore{a 5\%} better accuracy at a minimum and produces additional speedup over GoolgleNet throughout the KITTI object detection benchmark data set in a real-time object detection system.

arXiv:2111.07975공식 코드 · Papers with Code

Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement

Object rearrangement has recently emerged as a key competency in robot manipulation, with practical solutions generally involving object detection, recognition, grasping and high-level planning. Goal-images describing a desired scene configuration are a promising and increasingly used mode of instruction. A key outstanding challenge is the accurate inference of matches between objects in front of a robot, and those seen in a provided goal image, where recent works have struggled in the absence of object-specific training data. In this work, we explore the deterioration of existing methods' ability to infer matches between objects as the visual shift between observed and goal scenes increases. We find that a fundamental limitation of the current setting is that source and target images must contain the same $\textit{instance}$ of every object, which restricts practical deployment. We present a novel approach to object matching that uses a large pre-trained vision-language model to match objects in a cross-instance setting by leveraging semantics together with visual features as a more robust, and much more general, measure of similarity. We demonstrate that this provides considerably improved matching performance in cross-instance settings, and can be used to guide multi-object rearrangement with a robot manipulator from an image that shares no object $\textit{instances}$ with the robot's scene.

arXiv:2111.07548

Unsupervised Lightweight Single Object Tracking with UHP-SOT++

An unsupervised, lightweight and high-performance single object tracker, called UHP-SOT, was proposed by Zhou et al. recently. As an extension, we present an enhanced version and name it UHP-SOT++ in this work. Built upon the foundation of the discriminative-correlation-filters-based (DCF-based) tracker, two new ingredients are introduced in UHP-SOT and UHP-SOT++: 1) background motion modeling and 2) object box trajectory modeling. The main difference between UHP-SOT and UHP-SOT++ is the fusion strategy of proposals from three models (i.e., DCF, background motion and object box trajectory models). An improved fusion strategy is adopted by UHP-SOT++ for more robust tracking performance against large-scale tracking datasets. Our second contribution lies in an extensive evaluation of the performance of state-of-the-art supervised and unsupervised methods by testing them on four SOT benchmark datasets - OTB2015, TC128, UAV123 and LaSOT. Experiments show that UHP-SOT++ outperforms all previous unsupervised methods and several deep-learning (DL) methods in tracking accuracy. Since UHP-SOT++ has extremely small model size, high tracking performance, and low computational complexity (operating at a rate of 20 FPS on an i5 CPU even without code optimization), it is an ideal solution in real-time object tracking on resource-limited platforms. Based on the experimental results, we compare pros and cons of supervised and unsupervised trackers and provide a new perspective to understand the performance gap between supervised and unsupervised methods, which is the third contribution of this work.

arXiv:2111.07370공식 코드 · Papers with Code

Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks

Video-based computer vision tasks can benefit from estimation of the salient regions and interactions between those regions. Traditionally, this has been done by identifying the object regions in the images by utilizing pre-trained models to perform object detection, object segmentation and/or object pose estimation. Although using pre-trained models is a viable approach, it has several limitations in the need for an exhaustive annotation of object categories, a possible domain gap between datasets, and a bias that is typically present in pre-trained models. In this work, we propose to utilize the common rationale that a sequence of video frames capture a set of common objects and interactions between them, thus a notion of co-segmentation between the video frame features may equip the model with the ability to automatically focus on task-specific salient regions and improve the underlying task's performance in an end-to-end manner. In this regard, we propose a generic module called ``Co-Segmentation inspired Attention Module'' (COSAM) that can be plugged in to any CNN model to promote the notion of co-segmentation based attention among a sequence of video frame features. We show the application of COSAM in three video-based tasks namely: 1) Video-based person re-ID, 2) Video captioning, & 3) Video action classification and demonstrate that COSAM is able to capture the task-specific salient regions in video frames, thus leading to notable performance improvements along with interpretable attention maps for a variety of video-based vision tasks, with possible application to other video-based vision tasks as well.

arXiv:2111.07117공식 코드 · Papers with Code

Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views

Learning object-centric representations of multi-object scenes is a promising approach towards machine intelligence, facilitating high-level reasoning and control from visual sensory data. However, current approaches for unsupervised object-centric scene representation are incapable of aggregating information from multiple observations of a scene. As a result, these "single-view" methods form their representations of a 3D scene based only on a single 2D observation (view). Naturally, this leads to several inaccuracies, with these methods falling victim to single-view spatial ambiguities. To address this, we propose The Multi-View and Multi-Object Network (MulMON) -- a method for learning accurate, object-centric representations of multi-object scenes by leveraging multiple views. In order to sidestep the main technical difficulty of the multi-object-multi-view scenario -- maintaining object correspondences across views -- MulMON iteratively updates the latent object representations for a scene over multiple views. To ensure that these iterative updates do indeed aggregate spatial information to form a complete 3D scene understanding, MulMON is asked to predict the appearance of the scene from novel viewpoints during training. Through experiments, we show that MulMON better-resolves spatial ambiguities than single-view methods -- learning more accurate and disentangled object representations -- and also achieves new functionality in predicting object segmentations for novel viewpoints.

arXiv:2111.07898공식 코드 · Papers with Code

Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization

Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks, especially in challenging conditions such as cluttered images. However, little is known about the exact computational role of recurrent information flow in these conditions. Here we test RNNs trained for object categorization on the hypothesis that recurrence iteratively aids object categorization via the communication of category-orthogonal auxiliary variables (the location, orientation, and scale of the object). Using diagnostic linear readouts, we find that: (a) information about auxiliary variables increases across time in all network layers, (b) this information is indeed present in the recurrent information flow, and (c) its manipulation significantly affects task performance. These observations confirm the hypothesis that category-orthogonal auxiliary variable information is conveyed through recurrent connectivity and is used to optimize category inference in cluttered environments.

arXiv:2111.06425공식 코드 · Papers with Code

Multiple Hypothesis Hypergraph Tracking for Posture Identification in Embryonic Caenorhabditis elegans

Current methods in multiple object tracking (MOT) rely on independent object trajectories undergoing predictable motion to effectively track large numbers of objects. Adversarial conditions such as volatile object motion and imperfect detections create a challenging tracking landscape in which established methods may yield inadequate results. Multiple hypothesis hypergraph tracking (MHHT) is developed to perform MOT among interdependent objects amid noisy detections. The method extends traditional multiple hypothesis tracking (MHT) via hypergraphs to model correlated object motion, allowing for robust tracking in challenging scenarios. MHHT is applied to perform seam cell tracking during late-stage embryogenesis in embryonic C. elegans.

arXiv:2111.06276

6D Pose Estimation with Combined Deep Learning and 3D Vision Techniques for a Fast and Accurate Object Grasping

Real-time robotic grasping, supporting a subsequent precise object-in-hand operation task, is a priority target towards highly advanced autonomous systems. However, such an algorithm which can perform sufficiently-accurate grasping with time efficiency is yet to be found. This paper proposes a novel method with a 2-stage approach that combines a fast 2D object recognition using a deep neural network and a subsequent accurate and fast 6D pose estimation based on Point Pair Feature framework to form a real-time 3D object recognition and grasping solution capable of multi-object class scenes. The proposed solution has a potential to perform robustly on real-time applications, requiring both efficiency and accuracy. In order to validate our method, we conducted extensive and thorough experiments involving laborious preparation of our own dataset. The experiment results show that the proposed method scores 97.37% accuracy in 5cm5deg metric and 99.37% in Average Distance metric. Experiment results have shown an overall 62% relative improvement (5cm5deg metric) and 52.48% (Average Distance metric) by using the proposed method. Moreover, the pose estimation execution also showed an average improvement of 47.6% in running time. Finally, to illustrate the overall efficiency of the system in real-time operations, a pick-and-place robotic experiment is conducted and has shown a convincing success rate with 90% of accuracy. This experiment video is available at https://sites.google.com/view/dl-ppf6dpose/.

arXiv:2111.06069

CodEx: A Modular Framework for Joint Temporal De-blurring and Tomographic Reconstruction

In many computed tomography (CT) imaging applications, it is important to rapidly collect data from an object that is moving or changing with time. Tomographic acquisition is generally assumed to be step-and-shoot, where the object is rotated to each desired angle, and a view is taken. However, step-and-shoot acquisition is slow and can waste photons, so in practice fly-scanning is done where the object is continuously rotated while collecting data. However, this can result in motion-blurred views and consequently reconstructions with severe motion artifacts. In this paper, we introduce CodEx, a modular framework for joint de-blurring and tomographic reconstruction that can effectively invert the motion blur introduced in sparse view fly-scanning. The method is a synergistic combination of a novel acquisition method with a novel non-convex Bayesian reconstruction algorithm. CodEx works by encoding the acquisition with a known binary code that the reconstruction algorithm then inverts. Using a well chosen binary code to encode the measurements can improve the accuracy of the inversion process. The CodEx reconstruction method uses the alternating direction method of multipliers (ADMM) to split the inverse problem into iterative deblurring and reconstruction sub-problems, making reconstruction practical to implement. We present reconstruction results on both simulated and binned experimental data to demonstrate the effectiveness of our method.

arXiv:2111.05615

Leveraging Geometry for Shape Estimation from a Single RGB Image

Predicting 3D shapes and poses of static objects from a single RGB image is an important research area in modern computer vision. Its applications range from augmented reality to robotics and digital content creation. Typically this task is performed through direct object shape and pose predictions which is inaccurate. A promising research direction ensures meaningful shape predictions by retrieving CAD models from large scale databases and aligning them to the objects observed in the image. However, existing work does not take the object geometry into account, leading to inaccurate object pose predictions, especially for unseen objects. In this work we demonstrate how cross-domain keypoint matches from an RGB image to a rendered CAD model allow for more precise object pose predictions compared to ones obtained through direct predictions. We further show that keypoint matches can not only be used to estimate the pose of an object, but also to modify the shape of the object itself. This is important as the accuracy that can be achieved with object retrieval alone is inherently limited to the available CAD models. Allowing shape adaptation bridges the gap between the retrieved CAD model and the observed shape. We demonstrate our approach on the challenging Pix3D dataset. The proposed geometric shape prediction improves the AP mesh over the state-of-the-art from 33.2 to 37.8 on seen objects and from 8.2 to 17.1 on unseen objects. Furthermore, we demonstrate more accurate shape predictions without closely matching CAD models when following the proposed shape adaptation. Code is publicly available at https://github.com/florianlanger/leveraging_geometry_for_shape_estimation .

arXiv:2111.05393

Object-Centric Representation Learning with Generative Spatial-Temporal Factorization

Learning object-centric scene representations is essential for attaining structural understanding and abstraction of complex scenes. Yet, as current approaches for unsupervised object-centric representation learning are built upon either a stationary observer assumption or a static scene assumption, they often: i) suffer single-view spatial ambiguities, or ii) infer incorrectly or inaccurately object representations from dynamic scenes. To address this, we propose Dynamics-aware Multi-Object Network (DyMON), a method that broadens the scope of multi-view object-centric representation learning to dynamic scenes. We train DyMON on multi-view-dynamic-scene data and show that DyMON learns -- without supervision -- to factorize the entangled effects of observer motions and scene object dynamics from a sequence of observations, and constructs scene object spatial representations suitable for rendering at arbitrary times (querying across time) and from arbitrary viewpoints (querying across space). We also show that the factorized scene representations (w.r.t. objects) support querying about a single object by space and time independently.

arXiv:2111.05251

Learning Perceptual Concepts by Bootstrapping from Human Queries

When robots operate in human environments, it's critical that humans can quickly teach them new concepts: object-centric properties of the environment that they care about (e.g. objects near, upright, etc). However, teaching a new perceptual concept from high-dimensional robot sensor data (e.g. point clouds) is demanding, requiring an unrealistic amount of human labels. To address this, we propose a framework called Perceptual Concept Bootstrapping (PCB). First, we leverage the inherently lower-dimensional privileged information, e.g., object poses and bounding boxes, available from a simulator only at training time to rapidly learn a low-dimensional, geometric concept from minimal human input. Second, we treat this low-dimensional concept as an automatic labeler to synthesize a large-scale high-dimensional data set with the simulator. With these two key ideas, PCB alleviates human label burden while still learning perceptual concepts that work with real sensor input where no privileged information is available. We evaluate PCB for learning spatial concepts that describe object state or multi-object relationships, and show it achieves superior performance compared to baseline methods. We also demonstrate the utility of the learned concepts in motion planning tasks on a 7-DoF Franka Panda robot.

arXiv:2111.04265

Adaptive area-preserving parameterization of open and closed anatomical surfaces

The parameterization of open and closed anatomical surfaces is of fundamental importance in many biomedical applications. Spherical harmonics, a set of basis functions defined on the unit sphere, are widely used for anatomical shape description. However, establishing a one-to-one correspondence between the object surface and the entire unit sphere may induce a large geometric distortion in case the shape of the surface is too different from a perfect sphere. In this work, we propose adaptive area-preserving parameterization methods for simply-connected open and closed surfaces with the target of the parameterization being a spherical cap. Our methods optimize the shape of the parameter domain along with the mapping from the object surface to the parameter domain. The object surface will be globally mapped to an optimal spherical cap region of the unit sphere in an area-preserving manner while also exhibiting low conformal distortion. We further develop a set of spherical harmonics-like basis functions defined over the adaptive spherical cap domain, which we call the adaptive harmonics. Experimental results show that the proposed parameterization methods outperform the existing methods for both open and closed anatomical surfaces in terms of area and angle distortion. Surface description of the object surfaces can be effectively achieved using a novel combination of the adaptive parameterization and the adaptive harmonics. Our work provides a novel way of mapping anatomical surfaces with improved accuracy and greater flexibility. More broadly, the idea of using an adaptive parameter domain allows easy handling of a wide range of biomedical shapes.

arXiv:2111.03821공식 코드 · Papers with Code

ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking

6D object pose tracking has been extensively studied in the robotics and computer vision communities. The most promising solutions, leveraging on deep neural networks and/or filtering and optimization, exhibit notable performance on standard benchmarks. However, to our best knowledge, these have not been tested thoroughly against fast object motions. Tracking performance in this scenario degrades significantly, especially for methods that do not achieve real-time performance and introduce non negligible delays. In this work, we introduce ROFT, a Kalman filtering approach for 6D object pose and velocity tracking from a stream of RGB-D images. By leveraging real-time optical flow, ROFT synchronizes delayed outputs of low frame rate Convolutional Neural Networks for instance segmentation and 6D object pose estimation with the RGB-D input stream to achieve fast and precise 6D object pose and velocity tracking. We test our method on a newly introduced photorealistic dataset, Fast-YCB, which comprises fast moving objects from the YCB model set, and on the dataset for object and hand pose estimation HO-3D. Results demonstrate that our approach outperforms state-of-the-art methods for 6D object pose tracking, while also providing 6D object velocity tracking. A video showing the experiments is provided as supplementary material.

arXiv:2111.03751

Asynchronous Collaborative Localization by Integrating Spatiotemporal Graph Learning with Model-Based Estimation

Collaborative localization is an essential capability for a team of robots such as connected vehicles to collaboratively estimate object locations from multiple perspectives with reliant cooperation. To enable collaborative localization, four key challenges must be addressed, including modeling complex relationships between observed objects, fusing observations from an arbitrary number of collaborating robots, quantifying localization uncertainty, and addressing latency of robot communications. In this paper, we introduce a novel approach that integrates uncertainty-aware spatiotemporal graph learning and model-based state estimation for a team of robots to collaboratively localize objects. Specifically, we introduce a new uncertainty-aware graph learning model that learns spatiotemporal graphs to represent historical motions of the objects observed by each robot over time and provides uncertainties in object localization. Moreover, we propose a novel method for integrated learning and model-based state estimation, which fuses asynchronous observations obtained from an arbitrary number of robots for collaborative localization. We evaluate our approach in two collaborative object localization scenarios in simulations and on real robots. Experimental results show that our approach outperforms previous methods and achieves state-of-the-art performance on asynchronous collaborative localization.

논문 ID: document/9272784

Arbitrary-Oriented Object Detection in Remote Sensing Images Based on Polar Coordinates

Arbitrary-oriented object detection is an important task in the field of remote sensing object detection. Existing studies have shown that the polar coordinate system has obvious advantages in dealing with the problem of rotating object modeling, that is, using fewer parameters to achieve more accurate rotating object detection. However, present state-of-the-art detectors based on deep learning are all modeled in Cartesian coordinates. In this article, we introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet), which can achieve competitive detection accuracy via using simpler object representation model and less regression parameters. In P-RSDet method, arbitrary-oriented object detection can be achieved by predicting the center point and regressing one polar radius and two polar angles. Besides, in order to express the geometric constraint relationship between the polar radius and the polar angle, a Polar Ring Area Loss function is proposed to improve the prediction accuracy of the corner position. Experiments on DOTA, UCAS-AOD and NWPU VHR-10 datasets show that our P-RSDet achieves state-of-the-art performances with simpler model and less regression parameters.