PyTorchKR Papers

최신 논문

총 9,714편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2004.10518

Human and Machine Action Prediction Independent of Object Information

Predicting other people's action is key to successful social interactions, enabling us to adjust our own behavior to the consequence of the others' future actions. Studies on action recognition have focused on the importance of individual visual features of objects involved in an action and its context. Humans, however, recognize actions on unknown objects or even when objects are imagined (pantomime). Other cues must thus compensate the lack of recognizable visual object features. Here, we focus on the role of inter-object relations that change during an action. We designed a virtual reality setup and tested recognition speed for 10 different manipulation actions on 50 subjects. All objects were abstracted by emulated cubes so the actions could not be inferred using object information. Instead, subjects had to rely only on the information that comes from the changes in the spatial relations that occur between those cubes. In spite of these constraints, our results show the subjects were able to predict actions in, on average, less than 64% of the action's duration. We employed a computational model -an enriched Semantic Event Chain (eSEC)- incorporating the information of spatial relations, specifically (a) objects' touching/untouching, (b) static spatial relations between objects and (c) dynamic spatial relations between objects. Trained on the same actions as those observed by subjects, the model successfully predicted actions even better than humans. Information theoretical analysis shows that eSECs optimally use individual cues, whereas humans presumably mostly rely on a mixed-cue strategy, which takes longer until recognition. Providing a better cognitive basis of action recognition may, on one hand improve our understanding of related human pathologies and, on the other hand, also help to build robots for conflict-free human-robot cooperation. Our results open new avenues here.

arXiv:2004.09821공식 코드 · Papers with Code

Instance Segmentation of Biomedical Images with an Object-aware Embedding Learned with Local Constraints

Automatic instance segmentation is a problem that occurs in many biomedical applications. State-of-the-art approaches either perform semantic segmentation or refine object bounding boxes obtained from detection methods. Both suffer from crowded objects to varying degrees, merging adjacent objects or suppressing a valid object. In this work, we assign an embedding vector to each pixel through a deep neural network. The network is trained to output embedding vectors of similar directions for pixels from the same object, while adjacent objects are orthogonal in the embedding space, which effectively avoids the fusion of objects in a crowd. Our method yields state-of-the-art results even with a light-weighted backbone network on a cell segmentation (BBBC006 + DSB2018) and a leaf segmentation data set (CVPPP2017). The code and model weights are public available.

arXiv:2004.08644

A Deep Learning Approach to Object Affordance Segmentation

Learning to understand and infer object functionalities is an important step towards robust visual intelligence. Significant research efforts have recently focused on segmenting the object parts that enable specific types of human-object interaction, the so-called "object affordances". However, most works treat it as a static semantic segmentation problem, focusing solely on object appearance and relying on strong supervision and object detection. In this paper, we propose a novel approach that exploits the spatio-temporal nature of human-object interaction for affordance segmentation. In particular, we design an autoencoder that is trained using ground-truth labels of only the last frame of the sequence, and is able to infer pixel-wise affordance labels in both videos and static images. Our model surpasses the need for object labels and bounding boxes by using a soft-attention mechanism that enables the implicit localization of the interaction hotspot. For evaluation purposes, we introduce the SOR3D-AFF corpus, which consists of human-object interaction sequences and supports 9 types of affordances in terms of pixel-wise annotation, covering typical manipulations of tool-like objects. We show that our model achieves competitive results compared to strongly supervised methods on SOR3D-AFF, while being able to predict affordances for similar unseen objects in two affordance image-only datasets.

arXiv:2004.09039

X-Ray: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions

For applications in e-commerce, warehouses, healthcare, and home service, robots are often required to search through heaps of objects to grasp a specific target object. For mechanical search, we introduce X-Ray, an algorithm based on learned occupancy distributions. We train a neural network using a synthetic dataset of RGBD heap images labeled for a set of standard bounding box targets with varying aspect ratios. X-Ray minimizes support of the learned distribution as part of a mechanical search policy in both simulated and real environments. We benchmark these policies against two baseline policies on 1,000 heaps of 15 objects in simulation where the target object is partially or fully occluded. Results suggest that X-Ray is significantly more efficient, as it succeeds in extracting the target object 82% of the time, 15% more often than the best-performing baseline. Experiments on an ABB YuMi robot with 20 heaps of 25 household objects suggest that the learned policy transfers easily to a physical system, where it outperforms baseline policies by 15% in success rate with 17% fewer actions. Datasets, videos, and experiments are available at https://sites.google.com/berkeley.edu/x-ray.

arXiv:2004.09374

Complex-Object Visual Inspection via Multiple Lighting Configurations

The design of an automatic visual inspection system is usually performed in two stages. While the first stage consists in selecting the most suitable hardware setup for highlighting most effectively the defects on the surface to be inspected, the second stage concerns the development of algorithmic solutions to exploit the potentials offered by the collected data. In this paper, first, we present a novel illumination setup embedding four illumination configurations to resemble diffused, dark-field, and front lighting techniques. Second, we analyze the contributions brought by deploying the proposed setup in training phase only - mimicking the scenario in which an already developed visual inspection system cannot be modified on the customer site - and in evaluation phase. Along with an exhaustive set of experiments, in this paper, we demonstrate the suitability of the proposed setup for effective illumination of complex-objects, defined as manufactured items with variable surface characteristics that cannot be determined a priori. Moreover, we discuss the importance of multiple light configurations availability during training and their natural boosting effect which, without the need to modify the system design in evaluation phase, lead to improvements in the overall system performance.

arXiv:2004.09305

Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking

Directly learning multiple 3D objects motion from sequential images is difficult, while the geometric bundle adjustment lacks the ability to localize the invisible object centroid. To benefit from both the powerful object understanding skill from deep neural network meanwhile tackle precise geometry modeling for consistent trajectory estimation, we propose a joint spatial-temporal optimization-based stereo 3D object tracking method. From the network, we detect corresponding 2D bounding boxes on adjacent images and regress an initial 3D bounding box. Dense object cues (local depth and local coordinates) that associating to the object centroid are then predicted using a region-based network. Considering both the instant localization accuracy and motion consistency, our optimization models the relations between the object centroid and observed cues into a joint spatial-temporal error function. All historic cues will be summarized to contribute to the current estimation by a per-frame marginalization strategy without repeated computation. Quantitative evaluation on the KITTI tracking dataset shows our approach outperforms previous image-based 3D tracking methods by significant margins. We also report extensive results on multiple categories and larger datasets (KITTI raw and Argoverse Tracking) for future benchmarking.

arXiv:2004.07950

Learning visual policies for building 3D shape categories

Manipulation and assembly tasks require non-trivial planning of actions depending on the environment and the final goal. Previous work in this domain often assembles particular instances of objects from known sets of primitives. In contrast, we aim to handle varying sets of primitives and to construct different objects of a shape category. Given a single object instance of a category, e.g. an arch, and a binary shape classifier, we learn a visual policy to assemble other instances of the same category. In particular, we propose a disassembly procedure and learn a state policy that discovers new object instances and their assembly plans in state space. We then render simulated states in the observation space and learn a heatmap representation to predict alternative actions from a given input image. To validate our approach, we first demonstrate its efficiency for building object categories in state space. We then show the success of our visual policies for building arches from different primitives. Moreover, we demonstrate (i) the reactive ability of our method to re-assemble objects using additional primitives and (ii) the robust performance of our policy for unseen primitives resembling building blocks used during training. Our visual assembly policies are trained with no real images and reach up to 95% success rate when evaluated on a real robot.

논문 ID: 0156.13901

An Object-Oriented Representation for Efficient Reinforcement Learning

Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces. We introduce Object-Oriented MDPs (OO-MDPs), a representation based on objects and their interactions, which is a natural way of modeling environments and offers important generalization opportunities. We introduce a learning algorithm for deterministic OO-MDPs and prove a polynomial bound on its sample complexity. We illustrate the performance gains of our representation and algorithm in the well-known Taxi domain, plus a real-life videogame.

arXiv:2004.08189

MOPT: Multi-Object Panoptic Tracking

Comprehensive understanding of dynamic scenes is a critical prerequisite for intelligent robots to autonomously operate in their environment. Research in this domain, which encompasses diverse perception problems, has primarily been focused on addressing specific tasks individually rather than modeling the ability to understand dynamic scenes holistically. In this paper, we introduce a novel perception task denoted as multi-object panoptic tracking (MOPT), which unifies the conventionally disjoint tasks of semantic segmentation, instance segmentation, and multi-object tracking. MOPT allows for exploiting pixel-level semantic information of 'thing' and 'stuff' classes, temporal coherence, and pixel-level associations over time, for the mutual benefit of each of the individual sub-problems. To facilitate quantitative evaluations of MOPT in a unified manner, we propose the soft panoptic tracking quality (sPTQ) metric. As a first step towards addressing this task, we propose the novel PanopticTrackNet architecture that builds upon the state-of-the-art top-down panoptic segmentation network EfficientPS by adding a new tracking head to simultaneously learn all sub-tasks in an end-to-end manner. Additionally, we present several strong baselines that combine predictions from state-of-the-art panoptic segmentation and multi-object tracking models for comparison. We present extensive quantitative and qualitative evaluations of both vision-based and LiDAR-based MOPT that demonstrate encouraging results.

arXiv:2004.08154공식 코드 · Papers with Code

Detailed 2D-3D Joint Representation for Human-Object Interaction

Human-Object Interaction (HOI) detection lies at the core of action understanding. Besides 2D information such as human/object appearance and locations, 3D pose is also usually utilized in HOI learning since its view-independence. However, rough 3D body joints just carry sparse body information and are not sufficient to understand complex interactions. Thus, we need detailed 3D body shape to go further. Meanwhile, the interacted object in 3D is also not fully studied in HOI learning. In light of these, we propose a detailed 2D-3D joint representation learning method. First, we utilize the single-view human body capture method to obtain detailed 3D body, face and hand shapes. Next, we estimate the 3D object location and size with reference to the 2D human-object spatial configuration and object category priors. Finally, a joint learning framework and cross-modal consistency tasks are proposed to learn the joint HOI representation. To better evaluate the 2D ambiguity processing capacity of models, we propose a new benchmark named Ambiguous-HOI consisting of hard ambiguous images. Extensive experiments in large-scale HOI benchmark and Ambiguous-HOI show impressive effectiveness of our method. Code and data are available at https://github.com/DirtyHarryLYL/DJ-RN.

arXiv:2004.08028

CPARR: Category-based Proposal Analysis for Referring Relationships

The task of referring relationships is to localize subject and object entities in an image satisfying a relationship query, which is given in the form of \texttt{<subject, predicate, object>}. This requires simultaneous localization of the subject and object entities in a specified relationship. We introduce a simple yet effective proposal-based method for referring relationships. Different from the existing methods such as SSAS, our method can generate a high-resolution result while reducing its complexity and ambiguity. Our method is composed of two modules: a category-based proposal generation module to select the proposals related to the entities and a predicate analysis module to score the compatibility of pairs of selected proposals. We show state-of-the-art performance on the referring relationship task on two public datasets: Visual Relationship Detection and Visual Genome.

arXiv:2004.07786

Multi-Object Tracking with Siamese Track-RCNN

Multi-object tracking systems often consist of a combination of a detector, a short term linker, a re-identification feature extractor and a solver that takes the output from these separate components and makes a final prediction. Differently, this work aims to unify all these in a single tracking system. Towards this, we propose Siamese Track-RCNN, a two stage detect-and-track framework which consists of three functional branches: (1) the detection branch localizes object instances; (2) the Siamese-based track branch estimates the object motion and (3) the object re-identification branch re-activates the previously terminated tracks when they re-emerge. We test our tracking system on two popular datasets of the MOTChallenge. Siamese Track-RCNN achieves significantly higher results than the state-of-the-art, while also being much more efficient, thanks to its unified design.

arXiv:2004.07193공식 코드 · Papers with Code

A Transductive Approach for Video Object Segmentation

Semi-supervised video object segmentation aims to separate a target object from a video sequence, given the mask in the first frame. Most of current prevailing methods utilize information from additional modules trained in other domains like optical flow and instance segmentation, and as a result they do not compete with other methods on common ground. To address this issue, we propose a simple yet strong transductive method, in which additional modules, datasets, and dedicated architectural designs are not needed. Our method takes a label propagation approach where pixel labels are passed forward based on feature similarity in an embedding space. Different from other propagation methods, ours diffuses temporal information in a holistic manner which take accounts of long-term object appearance. In addition, our method requires few additional computational overhead, and runs at a fast $\sim$37 fps speed. Our single model with a vanilla ResNet50 backbone achieves an overall score of 72.3 on the DAVIS 2017 validation set and 63.1 on the test set. This simple yet high performing and efficient method can serve as a solid baseline that facilitates future research. Code and models are available at \url{https://github.com/microsoft/transductive-vos.pytorch}.

arXiv:2004.06333

WQT and DG-YOLO: towards domain generalization in underwater object detection

A General Underwater Object Detector (GUOD) should perform well on most of underwater circumstances. However, with limited underwater dataset, conventional object detection methods suffer from domain shift severely. This paper aims to build a GUOD with small underwater dataset with limited types of water quality. First, we propose a data augmentation method Water Quality Transfer (WQT) to increase domain diversity of the original small dataset. Second, for mining the semantic information from data generated by WQT, DG-YOLO is proposed, which consists of three parts: YOLOv3, DIM and IRM penalty. Finally, experiments on original and synthetic URPC2019 dataset prove that WQT+DG-YOLO achieves promising performance of domain generalization in underwater object detection.

arXiv:2004.06468공식 코드 · Papers with Code

Self6D: Self-Supervised Monocular 6D Object Pose Estimation

6D object pose estimation is a fundamental problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even from monocular images. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this shortcoming, we propose the idea of monocular 6D pose estimation by means of self-supervised learning, removing the need for real annotations. After training our proposed network fully supervised with synthetic RGB data, we leverage recent advances in neural rendering to further self-supervise the model on unannotated real RGB-D data, seeking for a visually and geometrically optimal alignment. Extensive evaluations demonstrate that our proposed self-supervision is able to significantly enhance the model's original performance, outperforming all other methods relying on synthetic data or employing elaborate techniques from the domain adaptation realm.

arXiv:2004.06711공식 코드 · Papers with Code

Deformable Siamese Attention Networks for Visual Object Tracking

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 channel attention. The cross-attention is capable of aggregating rich contextual inter-dependencies between the target template and the search image, providing an implicit manner to adaptively update the target template. In addition, we design a region refinement module that computes depth-wise cross correlations between the attentional features for more accurate tracking. We conduct experiments on six benchmarks, where our method achieves new state of-the-art results, outperforming the strong baseline, SiamRPN++ [24], by 0.464->0.537 and 0.415->0.470 EAO on VOT 2016 and 2018. Our code is available at: https://github.com/msight-tech/research-siamattn.

arXiv:2004.06587

Walk the Lines: Object Contour Tracing CNN for Contour Completion of Ships

We develop a new contour tracing algorithm to enhance the results of the latest object contour detectors. The goal is to achieve a perfectly closed, 1 pixel wide and detailed object contour, since this type of contour could be analyzed using methods such as Fourier descriptors. Convolutional Neural Networks (CNNs) are rarely used for contour tracing. However, we find CNNs are tailor-made for this task and that's why we present the Walk the Lines (WtL) algorithm, a standard regression CNN trained to follow object contours. To make the first step, we train the CNN only on ship contours, but the principle is also applicable to other objects. Input data are the image and the associated object contour prediction of the recently published RefineContourNet. The WtL gets a center pixel, which defines an input section and an angle for rotating this section. Ideally, the center pixel moves on the contour, while the angle describes upcoming directional contour changes. The WtL predicts its steps pixelwise in a selfrouting way. To obtain a complete object contour the WtL runs in parallel at different image locations and the traces of its individual paths are summed. In contrast to the comparable Non-Maximum Suppression method, our approach produces connected contours with finer details. Finally, the object contour is binarized under the condition of being closed. In case all procedures work as desired, excellent ship segmentations with high IoUs are produced, showing details such as antennas and ship superstructures that are easily omitted by other segmentation methods.

arXiv:2004.06046

Object classification from randomized EEG trials

New results suggest strong limits to the feasibility of classifying human brain activity evoked from image stimuli, as measured through EEG. Considerable prior work suffers from a confound between the stimulus class and the time since the start of the experiment. A prior attempt to avoid this confound using randomized trials was unable to achieve results above chance in a statistically significant fashion when the data sets were of the same size as the original experiments. Here, we again attempt to replicate these experiments with randomized trials on a far larger (20x) dataset of 1,000 stimulus presentations of each of forty classes, all from a single subject. To our knowledge, this is the largest such EEG data collection effort from a single subject and is at the bounds of feasibility. We obtain classification accuracy that is marginally above chance and above chance in a statistically significant fashion, and further assess how accuracy depends on the classifier used, the amount of training data used, and the number of classes. Reaching the limits of data collection without substantial improvement in classification accuracy suggests limits to the feasibility of this enterprise.

arXiv:2004.05233

Shape Estimation for Elongated Deformable Object using B-spline Chained Multiple Random Matrices Model

In this paper, a B-spline chained multiple random matrices representation is proposed to model geometric characteristics of an elongated deformable object. The hyper degrees of freedom structure of the elongated deformable object make its shape estimation challenging. Based on the likelihood function of the proposed model, an expectation-maximization (EM) method is derived to estimate the shape of the elongated deformable object. A split and merge method based on the Euclidean minimum spanning tree (EMST) is proposed to provide initialization for the EM algorithm. The proposed algorithm is evaluated for the shape estimation of the elongated deformable objects in scenarios, such as the static rope with various configurations (including configurations with intersection), the continuous manipulation of a rope and a plastic tube, and the assembly of two plastic tubes. The execution time is computed and the accuracy of the shape estimation results is evaluated based on the comparisons between the estimated width values and its ground-truth, and the intersection over union (IoU) metric.

arXiv:2004.05310

Probabilistic Oriented Object Detection in Automotive Radar

Autonomous radar has been an integral part of advanced driver assistance systems due to its robustness to adverse weather and various lighting conditions. Conventional automotive radars use digital signal processing (DSP) algorithms to process raw data into sparse radar pins that do not provide information regarding the size and orientation of the objects. In this paper, we propose a deep-learning based algorithm for radar object detection. The algorithm takes in radar data in its raw tensor representation and places probabilistic oriented bounding boxes around the detected objects in bird's-eye-view space. We created a new multimodal dataset with 102544 frames of raw radar and synchronized LiDAR data. To reduce human annotation effort we developed a scalable pipeline to automatically annotate ground truth using LiDAR as reference. Based on this dataset we developed a vehicle detection pipeline using raw radar data as the only input. Our best performing radar detection model achieves 77.28\% AP under oriented IoU of 0.3. To the best of our knowledge, this is the first attempt to investigate object detection with raw radar data for conventional corner automotive radars.