首页/论文/1904.11141

arXiv 1904.111412019-04-25cs.CV

HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection

Tsinghua University（清华大学）

Ya-Li Li, Shengjin Wang

DOI：: 10.1109/TIP.2019.2957850

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Object detection has been a challenging task in computer vision. Although significant progress has been made in object detection with deep neural networks, the attention mechanism is far from development. In this paper, we propose the hybrid attention mechanism for single-stage object detection. First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection. In particular, stacked dilated convolution layers with symmetrically fixed rates are constructed to learn spatial attention. The channel attention is proposed with the cross-level group normalization and squeeze-and-excitation module. Aligned attention is constructed with organized deformable filters. Second, the three kinds of attention are unified to construct the hybrid attention mechanism. We then embed the hybrid attention into Retina-Net and propose the efficient single-stage HAR-Net for object detection. The attention modules and the proposed HAR-Net are evaluated on the COCO detection dataset. Experiments demonstrate that hybrid attention can significantly improve the detection accuracy and the HAR-Net can achieve the state-of-the-art 45.8\% mAP, outperform existing single-stage object detectors.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

New York University（纽约大学）

This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.

2014-09-17cs.CV

Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network

Eindhoven University of Technology（埃因霍温理工大学）

We present a single network method for panoptic segmentation. This method combines the predictions from a jointly trained semantic and instance segmentation network using heuristics. Joint training is the first step towards an end-to-end panoptic segmentation network and is faster and more memory efficient than training and predicting with two networks, as done in previous work. The architecture consists of a ResNet-50 feature extractor shared by the semantic segmentation and instance segmentation branch. For instance segmentation, a Mask R-CNN type of architecture is used, while the semantic …

2019-02-07cs.CV

U-Harmony: 通过通用和谐化提升分割模型的联合训练

U-Harmony: Enhancing Joint Training for Segmentation Models with Universal Harmonization

Washington University in St. Louis（华盛顿大学圣路易斯分校）；Yale University（耶鲁大学）；Tohoku University（东北大学）

U-Harmony通过通用和谐化方法提升分割模型的联合训练能力，实现异构数据集的统一学习与跨模态适应。

2026-01-21cs.CVcs.LG

GoalieNet：用于冰球中守门员、装备和球网姿态联合估计的多阶段网络

GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockey

University of Waterloo（滑铁卢大学）

本文提出多阶段深度神经网络GoalieNet，用于联合估计冰球中守门员、装备及球网的姿态，在NHL基准数据上29个关键点平均准确率达84%，证明了该联合估计方法的有效性。

2023-06-28cs.CVcs.LG

(Fusionformer):Exploiting the Joint Motion Synergy with Fusion Network Based On Transformer for 3D Human Pose Estimation

Hangzhou Research Institute, Xidian University（西安电子科技大学杭州研究院）；Xidian University（西安电子科技大学）

For the current 3D human pose estimation task, a group of methods mainly learn the rules of 2D-3D projection from spatial and temporal correlation. However, earlier methods model the global features of the entire body joint in the time domain, but ignore the motion trajectory of individual joint. The recent work [29] considers that there are differences in motion between different joints and deals with the temporal relationship of each joint separately. However, we found that different joints show the same movement trends under some specific actions. Therefore, our proposed Fusionformer method…

2022-10-30cs.AIcs.CV

Convolutional Neural Networks for joint object detection and pose estimation: A comparative study

Université Paris-Est（巴黎东大）

In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose. We identify different feature representations of oriented objects, and energies that lead a network to learn this representations. The choice of the representation is crucial since the pose of an object has a natural, continuous structure while its category is a discrete variable. We evaluate the different approaches on the joint object detection and pose estimation task of the Pascal3D+ benchmark using Average Viewpoint Precision. We show…

2015-02-28cs.CVcs.LGcs.NE

更多相关论文收起更多论文

Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks

Dublin City University（都柏林城市大学）

This paper introduces a new approach to automatically quantify the severity of knee OA using X-ray images. Automatically quantifying knee OA severity involves two steps: first, automatically localizing the knee joints; next, classifying the localized knee joint images. We introduce a new approach to automatically detect the knee joints using a fully convolutional neural network (FCN). We train convolutional neural networks (CNN) from scratch to automatically quantify the knee OA severity optimizing a weighted ratio of two loss functions: categorical cross-entropy and mean-squared loss. This jo…

2017-03-29cs.CV

Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network

National Institute of Standards and Technology（美国国家标准与技术研究院）；Colorado State University（科罗拉多州立大学）；West Virginia University（西弗吉尼亚大学）；University of Nebraska-Lincoln（内布拉斯加大学林肯分校）；Georgia Institute of Technology（佐治亚理工学院）；Twentieth Century Fox（二十世纪福克斯）；Starfleet Academy（星际舰队学院）；Tyrell Inc.（泰伦公司）

In many domestic and military applications, aerial vehicle detection and super-resolutionalgorithms are frequently developed and applied independently. However, aerial vehicle detection on super-resolved images remains a challenging task due to the lack of discriminative information in the super-resolved images. To address this problem, we propose a Joint Super-Resolution and Vehicle DetectionNetwork (Joint-SRVDNet) that tries to generate discriminative, high-resolution images of vehicles fromlow-resolution aerial images. First, aerial images are up-scaled by a factor of 4x using a Multi-scale…

2020-05-03cs.CV

Multi-level Contrast Network for Wearables-based Joint Activity Segmentation and Recognition

Shanghai Jiao Tong University（上海交通大学）；Huazhong University of Science and Technology（华中科技大学）

Human activity recognition (HAR) with wearables is promising research that can be widely adopted in many smart healthcare applications. In recent years, the deep learning-based HAR models have achieved impressive recognition performance. However, most HAR algorithms are susceptible to the multi-class windows problem that is essential yet rarely exploited. In this paper, we propose to relieve this challenging problem by introducing the segmentation technology into HAR, yielding joint activity segmentation and recognition. Especially, we introduce the Multi-Stage Temporal Convolutional Network (…

2022-08-16cs.AIcs.CV

通过语言、姿态和合成IMU的联合表示增强基于惯性传感器的手部HAR

Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs

DFKI（德国人工智能研究中心）；RPTU（莱茵兰-普法尔茨州工业大学）；HKUST(GZ)（香港科技大学（广州））

提出多模态对比学习框架Multi$^3$Net，通过联合学习文本、姿态和合成IMU表示，解决HAR标注数据稀缺问题，显著提升可穿戴设备对细微活动的识别性能。

2024-07-27cs.AIcs.CV

An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization

Electronics and Telecommunications Research Institute（电子与电信研究院）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Kyungnam University（庆南大学）

Recently, learned image compression methods have been actively studied. Among them, entropy-minimization based approaches have achieved superior results compared to conventional image codecs such as BPG and JPEG2000. However, the quality enhancement and rate-minimization are conflictively coupled in the process of image compression. That is, maintaining high image quality entails less compression and vice versa. However, by jointly training separate quality enhancement in conjunction with image compression, the coding efficiency can be improved. In this paper, we propose a novel joint learning…

2020-03-13cs.CVeess.IV

Deep Residual 3D U-Net for Joint Segmentation and Texture Classification of Nodules in Lung

In this work we present a method for lung nodules segmentation, their texture classification and subsequent follow-up recommendation from the CT image of lung. Our method consists of neural network model based on popular U-Net architecture family but modified for the joint nodule segmentation and its texture classification tasks and an ensemble-based model for the follow-up recommendation. This solution was evaluated within the LNDb medical imaging challenge and produced the best nodule segmentation result on the final leaderboard.

2020-06-26cs.CVcs.LGeess.IV