PyTorchKR Papers

최신 논문

총 9,714편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2007.12407공식 코드 · Papers with Code

Visual Compositional Learning for Human-Object Interaction Detection

Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible combinations of objects and verbs types forms a long-tail distribution. We devise a deep Visual Compositional Learning (VCL) framework, which is a simple yet efficient framework to effectively address this problem. VCL first decomposes an HOI representation into object and verb specific features, and then composes new interaction samples in the feature space via stitching the decomposed features. The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection. Extensive experiments demonstrate that the proposed VCL can effectively improve the generalization of HOI detection on HICO-DET and V-COCO and outperforms the recent state-of-the-art methods on HICO-DET. Code is available at https://github.com/zhihou7/VCL.

arXiv:2007.12392

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Detecting objects in 3D LiDAR data is a core technology for autonomous driving and other robotics applications. Although LiDAR data is acquired over time, most of the 3D object detection algorithms propose object bounding boxes independently for each frame and neglect the useful information available in the temporal domain. To address this problem, in this paper we propose a sparse LSTM-based multi-frame 3d object detection algorithm. We use a U-Net style 3D sparse convolution network to extract features for each frame's LiDAR point-cloud. These features are fed to the LSTM module together with the hidden and memory features from last frame to predict the 3d objects in the current frame as well as hidden and memory features that are passed to the next frame. Experiments on the Waymo Open Dataset show that our algorithm outperforms the traditional frame by frame approach by 7.5% [email omitted] and other multi-frame approaches by 1.2% while using less memory and computation per frame. To the best of our knowledge, this is the first work to use an LSTM for 3D object detection in sparse point clouds.

arXiv:2007.12348

Unsupervised Discovery of 3D Physical Objects from Video

We study the problem of unsupervised physical object discovery. While existing frameworks aim to decompose scenes into 2D segments based off each object's appearance, we explore how physics, especially object interactions, facilitates disentangling of 3D geometry and position of objects from video, in an unsupervised manner. Drawing inspiration from developmental psychology, our Physical Object Discovery Network (POD-Net) uses both multi-scale pixel cues and physical motion cues to accurately segment observable and partially occluded objects of varying sizes, and infer properties of those objects. Our model reliably segments objects on both synthetic and real scenes. The discovered object properties can also be used to reason about physical events.

arXiv:2007.12107

Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild

Detecting objects and estimating their viewpoints in images are key tasks of 3D scene understanding. Recent approaches have achieved excellent results on very large benchmarks for object detection and viewpoint estimation. However, performances are still lagging behind for novel object categories with few samples. In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation. We demonstrate on both tasks the benefits of guiding the network prediction with class-representative features extracted from data in different modalities: image patches for object detection, and aligned 3D models for viewpoint estimation. Despite its simplicity, our method outperforms state-of-the-art methods by a large margin on a range of datasets, including PASCAL and COCO for few-shot object detection, and Pascal3D+ and ObjectNet3D for few-shot viewpoint estimation. Furthermore, when the 3D model is not available, we introduce a simple category-agnostic viewpoint estimation method by exploiting geometrical similarities and consistent pose labelling across different classes. While it moderately reduces performance, this approach still obtains better results than previous methods in this setting. Last, for the first time, we tackle the combination of both few-shot tasks, on three challenging benchmarks for viewpoint estimation in the wild, ObjectNet3D, Pascal3D+ and Pix3D, showing very promising results.

arXiv:2007.12104

Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection

Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored. Recent studies have shown the effectiveness of self-learned top-down attention mechanisms in object detection and other vision tasks. The top-down attention, however, is less effective at improving the performance of few-shot detectors. Due to the insufficient training data, object detectors cannot effectively generate attention maps for few-shot examples. To improve the performance and interpretability of few-shot object detectors, we propose an attentive few-shot object detection network (AttFDNet) that takes the advantages of both top-down and bottom-up attention. Being task-agnostic, the bottom-up attention serves as a prior that helps detect and localize naturally salient objects. We further address specific challenges in few-shot object detection by introducing two novel loss terms and a hybrid few-shot learning strategy. Experimental results and visualization demonstrate the complementary nature of the two types of attention and their roles in few-shot object detection. Codes are available at https://github.com/chenxy99/AttFDNet.

arXiv:2007.12099공식 코드 · Papers with Code

PP-YOLO: An Effective and Efficient Implementation of Object Detector

Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary to sacrifice accuracy to ensure the infer speed of the detector in practice. Therefore, the balance between effectiveness and efficiency of object detector must be considered. The goal of this paper is to implement an object detector with relatively balanced effectiveness and efficiency that can be directly applied in actual application scenarios, rather than propose a novel detection model. Considering that YOLOv3 has been widely used in practice, we develop a new object detector based on YOLOv3. We mainly try to combine various existing tricks that almost not increase the number of model parameters and FLOPs, to achieve the goal of improving the accuracy of detector as much as possible while ensuring that the speed is almost unchanged. Since all experiments in this paper are conducted based on PaddlePaddle, we call it PP-YOLO. By combining multiple tricks, PP-YOLO can achieve a better balance between effectiveness (45.2% mAP) and efficiency (72.9 FPS), surpassing the existing state-of-the-art detectors such as EfficientDet and YOLOv4.Source code is at https://github.com/PaddlePaddle/PaddleDetection.

arXiv:2007.12075공식 코드 · Papers with Code

Representation Sharing for Fast Object Detector Search and Beyond

Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such capability, we propose an extremely efficient neural architecture search method, named Fast And Diverse (FAD), to better explore the optimal configuration of receptive fields and convolution types in the sub-networks for one-stage detectors. FAD consists of a designed search space and an efficient architecture search algorithm. The search space contains a rich set of diverse transformations designed specifically for object detection. To cope with the designed search space, a novel search algorithm termed Representation Sharing (RepShare) is proposed to effectively identify the best combinations of the defined transformations. In our experiments, FAD obtains prominent improvements on two types of one-stage detectors with various backbones. In particular, our FAD detector achieves 46.4 AP on MS-COCO (under single-scale testing), outperforming the state-of-the-art detectors, including the most recent NAS-based detectors, Auto-FPN (searched for 16 GPU-days) and NAS-FCOS (28 GPU-days), while significantly reduces the search cost to 0.6 GPU-days. Beyond object detection, we further demonstrate the generality of FAD on the more challenging instance segmentation, and expect it to benefit more tasks.

arXiv:2007.11924

Right for the Right Reason: Making Image Classification Robust

The effectiveness of Convolutional Neural Networks (CNNs)in classifying image data has been thoroughly demonstrated. In order to explain the classification to humans, methods for visualizing classification evidence have been developed in recent years. These explanations reveal that sometimes images are classified correctly, but for the wrong reasons,i.e., based on incidental evidence. Of course, it is desirable that images are classified correctly for the right reasons, i.e., based on the actual evidence. To this end, we propose a new explanation quality metric to measure object aligned explanation in image classification which we refer to as theObAlExmetric. Using object detection approaches, explanation approaches, and ObAlEx, we quantify the focus of CNNs on the actual evidence. Moreover, we show that additional training of the CNNs can improve the focus of CNNs without decreasing their accuracy.

arXiv:2007.11901공식 코드 · Papers with Code

Weakly Supervised 3D Object Detection from Lidar Point Cloud

It is laborious to manually label point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under weak supervision, i.e., only the horizontal centers of objects are click-annotated on bird's view scenes. Stage-2 learns to refine the cylindrical proposals to get cuboids and confidence scores, using a few well-labeled object instances. Using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves 85-95% the performance of current top-leading, fully supervised detectors (which require 3, 712 exhaustively and precisely annotated scenes with 15, 654 instances). More importantly, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, allowing both automatic and active working modes. The annotations generated by our model can be used to train 3D object detectors with over 94% of their original performance (under manually labeled data). Our experiments also show our model's potential in boosting performance given more training data. Above designs make our approach highly practical and introduce new opportunities for learning 3D object detection with reduced annotation burden.

arXiv:2007.11782공식 코드 · Papers with Code

Accurate RGB-D Salient Object Detection via Collaborative Learning

Benefiting from the spatial cues embedded in depth images, recent progress on RGB-D saliency detection shows impressive ability on some challenge scenarios. However, there are still two limitations. One hand is that the pooling and upsampling operations in FCNs might cause blur object boundaries. On the other hand, using an additional depth-network to extract depth features might lead to high computation and storage cost. The reliance on depth inputs during testing also limits the practical applications of current RGB-D models. In this paper, we propose a novel collaborative learning framework where edge, depth and saliency are leveraged in a more efficient way, which solves those problems tactfully. The explicitly extracted edge information goes together with saliency to give more emphasis to the salient regions and object boundaries. Depth and saliency learning is innovatively integrated into the high-level feature learning process in a mutual-benefit manner. This strategy enables the network to be free of using extra depth networks and depth inputs to make inference. To this end, it makes our model more lightweight, faster and more versatile. Experiment results on seven benchmark datasets show its superior performance.

arXiv:2007.11404공식 코드 · Papers with Code

A Hybrid Neuromorphic Object Tracking and Classification Framework for Real-time Systems

Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications. To address this challenge, this paper proposes a real-time, hybrid neuromorphic framework for object tracking and classification using event-based cameras that possess properties such as low-power consumption (5-14 mW) and high dynamic range (120 dB). Nonetheless, unlike traditional approaches of using event-by-event processing, this work uses a mixed frame and event approach to get energy savings with high performance. Using a frame-based region proposal method based on the density of foreground events, a hardware-friendly object tracking scheme is implemented using the apparent object velocity while tackling occlusion scenarios. The object track input is converted back to spikes for TrueNorth classification via the energy-efficient deep network (EEDN) pipeline. Using originally collected datasets, we train the TrueNorth model on the hardware track outputs, instead of using ground truth object locations as commonly done, and demonstrate the ability of our system to handle practical surveillance scenarios. As an optional paradigm, to exploit the low latency and asynchronous nature of neuromorphic vision sensors (NVS), we also propose a continuous-time tracker with C++ implementation where each event is processed individually. Thereby, we extensively compare the proposed methodologies to state-of-the-art event-based and frame-based methods for object tracking and classification, and demonstrate the use case of our neuromorphic approach for real-time and embedded applications without sacrificing performance. Finally, we also showcase the efficacy of the proposed system to a standard RGB camera setup when evaluated over several hours of traffic recordings.

arXiv:2007.11167공식 코드 · Papers with Code

Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference

Utilization of latent space to capture a lower-dimensional representation of a complex dynamics model is explored in this work. The targeted application is of a robotic manipulator executing a complex environment interaction task, in particular, cutting a wooden object. We train two flavours of Variational Autoencoders---standard and Vector-Quantised---to learn the latent space which is then used to infer certain properties of the cutting operation, such as whether the robot is cutting or not, as well as, material and geometry of the object being cut. The two VAE models are evaluated with reconstruction, prediction and a combined reconstruction/prediction decoders. The results demonstrate the expressiveness of the latent space for robotic interaction inference and the competitive prediction performance against recurrent neural networks.

arXiv:2007.11089

Accelerating Deep Learning Applications in Space

Computing at the edge offers intriguing possibilities for the development of autonomy and artificial intelligence. The advancements in autonomous technologies and the resurgence of computer vision have led to a rise in demand for fast and reliable deep learning applications. In recent years, the industry has introduced devices with impressive processing power to perform various object detection tasks. However, with real-time detection, devices are constrained in memory, computational capacity, and power, which may compromise the overall performance. This could be solved either by optimizing the object detector or modifying the images. In this paper, we investigate the performance of CNN-based object detectors on constrained devices when applying different image compression techniques. We examine the capabilities of a NVIDIA Jetson Nano; a low-power, high-performance computer, with an integrated GPU, small enough to fit on-board a CubeSat. We take a closer look at the Single Shot MultiBox Detector (SSD) and Region-based Fully Convolutional Network (R-FCN) that are pre-trained on DOTA - a Large Scale Dataset for Object Detection in Aerial Images. The performance is measured in terms of inference time, memory consumption, and accuracy. By applying image compression techniques, we are able to optimize performance. The two techniques applied, lossless compression and image scaling, improves speed and memory consumption with no or little change in accuracy. The image scaling technique achieves a 100% runnable dataset and we suggest combining both techniques in order to optimize the speed/memory/accuracy trade-off.

arXiv:2007.11056공식 코드 · Papers with Code

BorderDet: Border Feature for Dense Object Detection

Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted to generate the bounding box predictions. The point feature is convenient to use but may lack the explicit border information for accurate localization. In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature. Based on the BorderAlign, we design a novel detection architecture called BorderDet, which explicitly exploits the border information for stronger classification and more accurate localization. With ResNet-50 backbone, our method improves single-stage detector FCOS by 2.8 AP gains (38.6 v.s. 41.4). With the ResNeXt-101-DCN backbone, our BorderDet obtains 50.3 AP, outperforming the existing state-of-the-art approaches. The code is available at (https://github.com/Megvii-BaseDetection/BorderDet).

논문 ID: document/9123077

Development and evaluation of a test setup to investigate distance differences in immersive virtual environments

Nowadays, with recent advances in virtual reality technology, it is easily possible to integrate real objects into virtual environments by creating an exact virtual replication and enabling interaction with them by mapping the obtained tracking data of the real to the virtual objects. The primary goal of our study is to develop a system to investigate distance differences for near-field interaction in immersive virtual environments. In this context, the term distance difference refers to the shift between a real object and the respective replication of the real object in the virtual environment of the same size. This could occur for a number of reasons e.g. due to errors in motion tracking or mistakes in designing the virtual environment. Our virtual environment is developed using the Unity3D game engine, while the immersive contents were displayed on an HTC Vive Pro head-mounted display. The virtual room shown to the user includes a replication of the real testing lab environment, while one of the two real objects is tracked and mirrored to the virtual world using an HTC Vive Tracker. Both objects are present in the real as well as in the virtual world. To find perceivable distance differences in the near-field, the actual task in the subjective test was to pick up one object and place it into another object. The position of the static object in the virtual world is shifted by values between 0 and 4 cm, while the position of the real object is kept constant. The system is evaluated by conducting a subjective proof-of-concept test with 18 test subjects. The distance difference is evaluated by the subjects through estimating perceived confusion on a modified 5-point absolute category rating scale. The study provides quantitative insights into allowable real-world vs. virtual-world mismatch boundaries for near-field interactions, with a threshold value of around 1 cm.

arXiv:2007.10591

AinnoSeg: Panoramic Segmentation with High Perfomance

Panoramic segmentation is a scene where image segmentation tasks is more difficult. With the development of CNN networks, panoramic segmentation tasks have been sufficiently developed.However, the current panoramic segmentation algorithms are more concerned with context semantics, but the details of image are not processed enough. Moreover, they cannot solve the problems which contains the accuracy of occluded object segmentation,little object segmentation,boundary pixel in object segmentation etc. Aiming to address these issues, this paper presents some useful tricks. (a) By changing the basic segmentation model, the model can take into account the large objects and the boundary pixel classification of image details. (b) Modify the loss function so that it can take into account the boundary pixels of multiple objects in the image. (c) Use a semi-supervised approach to regain control of the training process. (d) Using multi-scale training and reasoning. All these operations named AinnoSeg, AinnoSeg can achieve state-of-art performance on the well-known dataset ADE20K.

arXiv:2007.10732공식 코드 · Papers with Code

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for building high-performance deep learning methods. Most existing semi-supervised segmentation approaches either tend to neglect geometric constraint in object segments, leading to incomplete object coverage, or impose strong shape prior that requires extra alignment. In this work, we propose a novel shapeaware semi-supervised segmentation strategy to leverage abundant unlabeled data and to enforce a geometric shape constraint on the segmentation output. To achieve this, we develop a multi-task deep network that jointly predicts semantic segmentation and signed distance map(SDM) of object surfaces. During training, we introduce an adversarial loss between the predicted SDMs of labeled and unlabeled data so that our network is able to capture shape-aware features more effectively. Experiments on the Atrial Segmentation Challenge dataset show that our method outperforms current state-of-the-art approaches with improved shape estimation, which validates its efficacy. Code is available at https://github.com/kleinzcy/SASSnet.

arXiv:2007.10720

Unsupervised Heterogeneous Coupling Learning for Categorical Representation

Complex categorical data is often hierarchically coupled with heterogeneous relationships between attributes and attribute values and the couplings between objects. Such value-to-object couplings are heterogeneous with complementary and inconsistent interactions and distributions. Limited research exists on unlabeled categorical data representations, ignores the heterogeneous and hierarchical couplings, underestimates data characteristics and complexities, and overuses redundant information, etc. The deep representation learning of unlabeled categorical data is challenging, overseeing such value-to-object couplings, complementarity and inconsistency, and requiring large data, disentanglement, and high computational power. This work introduces a shallow but powerful UNsupervised heTerogeneous couplIng lEarning (UNTIE) approach for representing coupled categorical data by untying the interactions between couplings and revealing heterogeneous distributions embedded in each type of couplings. UNTIE is efficiently optimized w.r.t. a kernel k-means objective function for unsupervised representation learning of heterogeneous and hierarchical value-to-object couplings. Theoretical analysis shows that UNTIE can represent categorical data with maximal separability while effectively represent heterogeneous couplings and disclose their roles in categorical data. The UNTIE-learned representations make significant performance improvement against the state-of-the-art categorical representations and deep representation models on 25 categorical data sets with diversified characteristics.

arXiv:2007.10665

Segmentation of the Left Ventricle by SDD double threshold selection and CHT

Automatic and robust segmentation of the left ventricle (LV) in magnetic resonance images (MRI) has remained challenging for many decades. With the great success of deep learning in object detection and classification, the research focus of LV segmentation has changed to convolutional neural network (CNN) in recent years. However, LV segmentation is a pixel-level classification problem and its categories are intractable compared to object detection and classification. In this paper, we proposed a robust LV segmentation method based on slope difference distribution (SDD) double threshold selection and circular Hough transform (CHT). The proposed method achieved 96.51% DICE score on the test set of automated cardiac diagnosis challenge (ACDC) which is higher than the best accuracy reported in recently published literatures.

arXiv:2007.10232

The Effect of Top-Down Attention in Occluded Object Recognition

This study is concerned with the top-down visual processing benefit in the task of occluded object recognition. To this end, a psychophysical experiment is designed and carried out which aimed at investigating the effect of consistency of contextual information on the recognition of objects which are partially occluded. The results demonstrate the facilitative impact of consistent contextual clues on the task of object recognition in presence of occlusion.