PyTorchKR Papers

최신 논문

총 9,714편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2012.04700

Emergence of Different Modes of Tool Use in a Reaching and Dragging Task

Tool use is an important milestone in the evolution of intelligence. In this paper, we investigate different modes of tool use that emerge in a reaching and dragging task. In this task, a jointed arm with a gripper must grab a tool (T, I, or L-shaped) and drag an object down to the target location (the bottom of the arena). The simulated environment had real physics such as gravity and friction. We trained a deep-reinforcement learning based controller (with raw visual and proprioceptive input) with minimal reward shaping information to tackle this task. We observed the emergence of a wide range of unexpected behaviors, not directly encoded in the motor primitives or reward functions. Examples include hitting the object to the target location, correcting error of initial contact, throwing the tool toward the object, as well as normal expected behavior such as wide sweep. Also, we further analyzed these behaviors based on the type of tool and the initial position of the target object. Our results show a rich repertoire of behaviors, beyond the basic built-in mechanisms of the deep reinforcement learning method we used.

arXiv:2012.04643공식 코드 · Papers with Code

The Lottery Ticket Hypothesis for Object Recognition

Recognition tasks, such as object recognition and keypoint estimation, have seen widespread adoption in recent years. Most state-of-the-art methods for these tasks use deep networks that are computationally expensive and have huge memory footprints. This makes it exceedingly difficult to deploy these systems on low power embedded devices. Hence, the importance of decreasing the storage requirements and the amount of computation in such models is paramount. The recently proposed Lottery Ticket Hypothesis (LTH) states that deep neural networks trained on large datasets contain smaller subnetworks that achieve on par performance as the dense networks. In this work, we perform the first empirical study investigating LTH for model pruning in the context of object detection, instance segmentation, and keypoint estimation. Our studies reveal that lottery tickets obtained from ImageNet pretraining do not transfer well to the downstream tasks. We provide guidance on how to find lottery tickets with up to 80% overall sparsity on different sub-tasks without incurring any drop in the performance. Finally, we analyse the behavior of trained tickets with respect to various task attributes such as object size, frequency, and difficulty of detection.

arXiv:2012.04634공식 코드 · Papers with Code

Accurate 3D Object Detection using Energy-Based Models

Accurate 3D object detection (3DOD) is crucial for safe navigation of complex environments by autonomous robots. Regressing accurate 3D bounding boxes in cluttered environments based on sparse LiDAR data is however a highly challenging problem. We address this task by exploring recent advances in conditional energy-based models (EBMs) for probabilistic regression. While methods employing EBMs for regression have demonstrated impressive performance on 2D object detection in images, these techniques are not directly applicable to 3D bounding boxes. In this work, we therefore design a differentiable pooling operator for 3D bounding boxes, serving as the core module of our EBM network. We further integrate this general approach into the state-of-the-art 3D object detector SA-SSD. On the KITTI dataset, our proposed approach consistently outperforms the SA-SSD baseline across all 3DOD metrics, demonstrating the potential of EBM-based regression for highly accurate 3DOD. Code is available at https://github.com/fregu856/ebms_3dod.

arXiv:2012.04382공식 코드 · Papers with Code

Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness in Object Detection

The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time, the average precision (AP) on clean images drops significantly. In this paper, we propose that using feature alignment of intermediate layer can improve clean AP and robustness in object detection. Further, on the basis of adversarial training, we present two feature alignment modules: Knowledge-Distilled Feature Alignment (KDFA) module and Self-Supervised Feature Alignment (SSFA) module, which can guide the network to generate more effective features. We conduct extensive experiments on PASCAL VOC and MS-COCO datasets to verify the effectiveness of our proposed approach. The code of our experiments is available at https://github.com/grispeut/Feature-Alignment.git.

arXiv:2012.04265

Learning to Generate Content-Aware Dynamic Detectors

Model efficiency is crucial for object detection. Mostprevious works rely on either hand-crafted design or auto-search methods to obtain a static architecture, regardless ofthe difference of inputs. In this paper, we introduce a newperspective of designing efficient detectors, which is automatically generating sample-adaptive model architectureon the fly. The proposed method is named content-aware dynamic detectors (CADDet). It first applies a multi-scale densely connected network with dynamic routing as the supernet. Furthermore, we introduce a course-to-fine strat-egy tailored for object detection to guide the learning of dynamic routing, which contains two metrics: 1) dynamic global budget constraint assigns data-dependent expectedbudgets for individual samples; 2) local path similarity regularization aims to generate more diverse routing paths. With these, our method achieves higher computational efficiency while maintaining good performance. To the best of our knowledge, our CADDet is the first work to introduce dynamic routing mechanism in object detection. Experiments on MS-COCO dataset demonstrate that CADDet achieves 1.8 higher mAP with 10% fewer FLOPs compared with vanilla routing strategy. Compared with the models based upon similar building blocks, CADDet achieves a 42% FLOPs reduction with a competitive mAP.

arXiv:2012.04150공식 코드 · Papers with Code

Dynamic Anchor Learning for Arbitrary-Oriented Object Detection

Arbitrary-oriented objects widely appear in natural scenes, aerial photographs, remote sensing images, etc., thus arbitrary-oriented object detection has received considerable attention. Many current rotation detectors use plenty of anchors with different orientations to achieve spatial alignment with ground truth boxes, then Intersection-over-Union (IoU) is applied to sample the positive and negative candidates for training. However, we observe that the selected positive anchors cannot always ensure accurate detections after regression, while some negative samples can achieve accurate localization. It indicates that the quality assessment of anchors through IoU is not appropriate, and this further lead to inconsistency between classification confidence and localization accuracy. In this paper, we propose a dynamic anchor learning (DAL) method, which utilizes the newly defined matching degree to comprehensively evaluate the localization potential of the anchors and carry out a more efficient label assignment process. In this way, the detector can dynamically select high-quality anchors to achieve accurate object detection, and the divergence between classification and regression will be alleviated. With the newly introduced DAL, we achieve superior detection performance for arbitrary-oriented objects with only a few horizontal preset anchors. Experimental results on three remote sensing datasets HRSC2016, DOTA, UCAS-AOD as well as a scene text dataset ICDAR 2015 show that our method achieves substantial improvement compared with the baseline model. Besides, our approach is also universal for object detection using horizontal bound box. The code and models are available at https://github.com/ming71/DAL.

arXiv:2012.04066

A New Window Loss Function for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation

Object detection methods are widely adopted for computer-aided diagnosis using medical images. Anomalous findings are usually treated as objects that are described by bounding boxes. Yet, many pathological findings, e.g., bone fractures, cannot be clearly defined by bounding boxes, owing to considerable instance, shape and boundary ambiguities. This makes bounding box annotations, and their associated losses, highly ill-suited. In this work, we propose a new bone fracture detection method for X-ray images, based on a labor effective and flexible annotation scheme suitable for abnormal findings with no clear object-level spatial extents or boundaries. Our method employs a simple, intuitive, and informative point-based annotation protocol to mark localized pathology information. To address the uncertainty in the fracture scales annotated via point(s), we convert the annotations into pixel-wise supervision that uses lower and upper bounds with positive, negative, and uncertain regions. A novel Window Loss is subsequently proposed to only penalize the predictions outside of the uncertain regions. Our method has been extensively evaluated on 4410 pelvic X-ray images of unique patients. Experiments demonstrate that our method outperforms previous state-of-the-art image classification and object detection baselines by healthy margins, with an AUROC of 0.983 and FROC score of 89.6%.

arXiv:2012.04060

Semantic and Geometric Modeling with Neural Message Passing in 3D Scene Graphs for Hierarchical Mechanical Search

Searching for objects in indoor organized environments such as homes or offices is part of our everyday activities. When looking for a target object, we jointly reason about the rooms and containers the object is likely to be in; the same type of container will have a different probability of having the target depending on the room it is in. We also combine geometric and semantic information to infer what container is best to search, or what other objects are best to move, if the target object is hidden from view. We propose to use a 3D scene graph representation to capture the hierarchical, semantic, and geometric aspects of this problem. To exploit this representation in a search process, we introduce Hierarchical Mechanical Search (HMS), a method that guides an agent's actions towards finding a target object specified with a natural language description. HMS is based on a novel neural network architecture that uses neural message passing of vectors with visual, geometric, and linguistic information to allow HMS to reason across layers of the graph while combining semantic and geometric cues. HMS is evaluated on a novel dataset of 500 3D scene graphs with dense placements of semantically related objects in storage locations, and is shown to be significantly better than several baselines at finding objects and close to the oracle policy in terms of the median number of actions required. Additional qualitative results can be found at https://ai.stanford.edu/mech-search/hms.

arXiv:2012.04027

Generating unseen complex scenes: are we there yet?

Although recent complex scene conditional generation models generate increasingly appealing scenes, it is very hard to assess which models perform better and why. This is often due to models being trained to fit different data splits, and defining their own experimental setups. In this paper, we propose a methodology to compare complex scene conditional generation models, and provide an in-depth analysis that assesses the ability of each model to (1) fit the training distribution and hence perform well on seen conditionings, (2) to generalize to unseen conditionings composed of seen object combinations, and (3) generalize to unseen conditionings composed of unseen object combinations. As a result, we observe that recent methods are able to generate recognizable scenes given seen conditionings, and exploit compositionality to generalize to unseen conditionings with seen object combinations. However, all methods suffer from noticeable image quality degradation when asked to generate images from conditionings composed of unseen object combinations. Moreover, through our analysis, we identify the advantages of different pipeline components, and find that (1) encouraging compositionality through instance-wise spatial conditioning normalizations increases robustness to both types of unseen conditionings, (2) using semantically aware losses such as the scene-graph perceptual similarity helps improve some dimensions of the generation process, and (3) enhancing the quality of generated masks and the quality of the individual objects are crucial steps to improve robustness to both types of unseen conditionings.

arXiv:2012.03768

Learning Tactile Models for Factor Graph-based Estimation

We're interested in the problem of estimating object states from touch during manipulation under occlusions. In this work, we address the problem of estimating object poses from touch during planar pushing. Vision-based tactile sensors provide rich, local image measurements at the point of contact. A single such measurement, however, contains limited information and multiple measurements are needed to infer latent object state. We solve this inference problem using a factor graph. In order to incorporate tactile measurements in the graph, we need local observation models that can map high-dimensional tactile images onto a low-dimensional state space. Prior work has used low-dimensional force measurements or engineered functions to interpret tactile measurements. These methods, however, can be brittle and difficult to scale across objects and sensors. Our key insight is to directly learn tactile observation models that predict the relative pose of the sensor given a pair of tactile images. These relative poses can then be incorporated as factors within a factor graph. We propose a two-stage approach: first we learn local tactile observation models supervised with ground truth data, and then integrate these models along with physics and geometric factors within a factor graph optimizer. We demonstrate reliable object tracking using only tactile feedback for 150 real-world planar pushing sequences with varying trajectories across three object shapes. Supplementary video: https://youtu.be/y1kBfSmi8w0

arXiv:2012.03597공식 코드 · Papers with Code

PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing Images

Object counting, which aims to count the accurate number of object instances in images, has been attracting more and more attention. However, challenges such as large scale variation, complex background interference, and non-uniform density distribution greatly limit the counting accuracy, particularly striking in remote sensing imagery. To mitigate the above issues, this paper proposes a novel framework for dense object counting in remote sensing images, which incorporates a pyramidal scale module (PSM) and a global context module (GCM), dubbed PSGCNet, where PSM is used to adaptively capture multi-scale information and GCM is to guide the model to select suitable scales generated from PSM. Moreover, a reliable supervision manner improved from Bayesian and Counting loss (BCL) is utilized to learn the density probability and then compute the count expectation at each annotation. It can relieve non-uniform density distribution to a certain extent. Extensive experiments on four remote sensing counting datasets demonstrate the effectiveness of the proposed method and the superiority of it compared with state-of-the-arts. Additionally, experiments extended on four commonly used crowd counting datasets further validate the generalization ability of the model. Code is available at https://github.com/gaoguangshuai/PSGCNet.

arXiv:2012.03519공식 코드 · Papers with Code

Fine-Grained Dynamic Head for Object Detection

The Feature Pyramid Network (FPN) presents a remarkable approach to alleviate the scale variance in object representation by performing instance-level assignments. Nevertheless, this strategy ignores the distinct characteristics of different sub-regions in an instance. To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation. Moreover, we design a spatial gate with the new activation function to reduce computational complexity dramatically through spatially sparse convolutions. Extensive experiments demonstrate the effectiveness and efficiency of the proposed method on several state-of-the-art detection benchmarks. Code is available at https://github.com/StevenGrove/DynamicHead.

arXiv:2012.03223공식 코드 · Papers with Code

Spatiotemporal tomography based on scattered multiangular signals and its application for resolving evolving clouds using moving platforms

We derive computed tomography (CT) of a time-varying volumetric translucent object, using a small number of moving cameras. We particularly focus on passive scattering tomography, which is a non-linear problem. We demonstrate the approach on dynamic clouds, as clouds have a major effect on Earth's climate. State of the art scattering CT assumes a static object. Existing 4D CT methods rely on a linear image formation model and often on significant priors. In this paper, the angular and temporal sampling rates needed for a proper recovery are discussed. If these rates are used, the paper leads to a representation of the time-varying object, which simplifies 4D CT tomography. The task is achieved using gradient-based optimization. We demonstrate this in physics-based simulations and in an experiment that had yielded real-world data.

arXiv:2012.03912

MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation

Navigation tasks in photorealistic 3D environments are challenging because they require perception and effective planning under partial observability. Recent work shows that map-like memory is useful for long-horizon navigation tasks. However, a focused investigation of the impact of maps on navigation tasks of varying complexity has not yet been performed. We propose the multiON task, which requires navigation to an episode-specific sequence of objects in a realistic environment. MultiON generalizes the ObjectGoal navigation task and explicitly tests the ability of navigation agents to locate previously observed goal objects. We perform a set of multiON experiments to examine how a variety of agent models perform across a spectrum of navigation task complexities. Our experiments show that: i) navigation performance degrades dramatically with escalating task complexity; ii) a simple semantic map agent performs surprisingly well relative to more complex neural image feature map agents; and iii) even oracle map agents achieve relatively low performance, indicating the potential for future work in training embodied navigation agents using maps. Video summary: https://youtu.be/yqTlHNIcgnY

arXiv:2012.02637

Global Context Aware RCNN for Object Detection

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively. Specifically, we leverage the dense connection to improve the information flow of the global context at different stages in the top-down process of FPN, and further use the attention mechanism to refine the global context at each level in the feature pyramid. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach.

arXiv:2012.02532공식 코드 · Papers with Code

DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning

We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning. Our robot interacts with objects using an initial action repertoire that is assumed to be acquired earlier and observes the effects it can create in the environment. To form action-grounded object, effect, and relational categories, we employ a binary bottleneck layer in a predictive, deep encoder-decoder network that takes the image of the scene and the action applied as input, and generates the resulting effects in the scene in pixel coordinates. After learning, the binary latent vector represents action-driven object categories based on the interaction experience of the robot. To distill the knowledge represented by the neural network into rules useful for symbolic reasoning, a decision tree is trained to reproduce its decoder function. Probabilistic rules are extracted from the decision paths of the tree and are represented in the Probabilistic Planning Domain Definition Language (PPDDL), allowing off-the-shelf planners to operate on the knowledge extracted from the sensorimotor experience of the robot. The deployment of the proposed approach for a simulated robotic manipulator enabled the discovery of discrete representations of object properties such as `rollable' and `insertable'. In turn, the use of these representations as symbols allowed the generation of effective plans for achieving goals, such as building towers of the desired height, demonstrating the effectiveness of the approach for multi-step object manipulation. Finally, we demonstrate that the system is not only restricted to the robotics domain by assessing its applicability to the MNIST 8-puzzle domain in which learned symbols allow for the generation of plans that move the empty tile into any given position.

arXiv:2012.02493

Compositionally Generalizable 3D Structure Prediction

Single-image 3D shape reconstruction is an important and long-standing problem in computer vision. A plethora of existing works is constantly pushing the state-of-the-art performance in the deep learning era. However, there remains a much more difficult and under-explored issue on how to generalize the learned skills over unseen object categories that have very different shape geometry distributions. In this paper, we bring in the concept of compositional generalizability and propose a novel framework that could better generalize to these unseen categories. We factorize the 3D shape reconstruction problem into proper sub-problems, each of which is tackled by a carefully designed neural sub-module with generalizability concerns. The intuition behind our formulation is that object parts (slates and cylindrical parts), their relationships (adjacency and translation symmetry), and shape substructures (T-junctions and a symmetric group of parts) are mostly shared across object categories, even though object geometries may look very different (e.g. chairs and cabinets). Experiments on PartNet show that we achieve superior performance than state-of-the-art. This validates our problem factorization and network designs.

arXiv:2012.02371

Scale-aware Insertion of Virtual Objects in Monocular Videos

In this paper, we propose a scale-aware method for inserting virtual objects with proper sizes into monocular videos. To tackle the scale ambiguity problem of geometry recovery from monocular videos, we estimate the global scale objects in a video with a Bayesian approach incorporating the size priors of objects, where the scene objects sizes should strictly conform to the same global scale and the possibilities of global scales are maximized according to the size distribution of object categories. To do so, we propose a dataset of sizes of object categories: Metric-Tree, a hierarchical representation of sizes of more than 900 object categories with the corresponding images. To handle the incompleteness of objects recovered from videos, we propose a novel scale estimation method that extracts plausible dimensions of objects for scale optimization. Experiments have shown that our method for scale estimation performs better than the state-of-the-art methods, and has considerable validity and robustness for different video scenes. Metric-Tree has been made available at: https://metric-tree.github.io

arXiv:2012.02206

Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

We introduce the task of dense captioning in 3D scans from commodity RGB-D sensors. As input, we assume a point cloud of a 3D scene; the expected output is the bounding boxes along with the descriptions for the underlying objects. To address the 3D object detection and description problems, we propose Scan2Cap, an end-to-end trained method, to detect objects in the input scene and describe them in natural language. We use an attention mechanism that generates descriptive tokens while referring to the related components in the local context. To reflect object relations (i.e. relative spatial relations) in the generated captions, we use a message passing graph module to facilitate learning object relation features. Our method can effectively localize and describe 3D objects in scenes from the ScanRefer dataset, outperforming 2D baseline methods by a significant margin (27.61% [email omitted]).

arXiv:2012.01950공식 코드 · Papers with Code

Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection

Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sparsely annotated object detection either re-weight the loss of hard negative samples or convert the unlabeled instances into ignored regions to reduce the interference of false negatives. We argue that these strategies are insufficient since they can at most alleviate the negative effect caused by missing annotations. In this paper, we propose a simple but effective mechanism, called Co-mining, for sparsely annotated object detection. In our Co-mining, two branches of a Siamese network predict the pseudo-label sets for each other. To enhance multi-view learning and better mine unlabeled instances, the original image and corresponding augmented image are used as the inputs of two branches of the Siamese network, respectively. Co-mining can serve as a general training mechanism applied to most of modern object detectors. Experiments are performed on MS COCO dataset with three different sparsely annotated settings using two typical frameworks: anchor-based detector RetinaNet and anchor-free detector FCOS. Experimental results show that our Co-mining with RetinaNet achieves 1.4%~2.1% improvements compared with different baselines and surpasses existing methods under the same sparsely annotated setting. Code is available at https://github.com/megvii-research/Co-mining.