首页/论文/1908.04385

arXiv 1908.043852019-08cs.CVcs.AIcs.LG

OD-GCN: Object Detection Boosted by Knowledge GCN

iQIYI Inc（爱奇艺公司）；Fudan University（复旦大学）

Zheng Liu, Zidong Jiang, Wei Feng, Hui Feng

备注：: 6 pages

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Classical CNN based object detection methods only extract the objects' image features, but do not consider the high-level relationship among objects in context. In this article, the graph convolutional networks (GCN) is integrated into the object detection framework to exploit the benefit of category relationship among objects, which is able to provide extra confidence for any pre-trained object detection model in our framework. In experiments, we test several popular base detection models on COCO dataset. The results show promising improvement on mAP by 1-5pp. In addition, visualized analysis reveals the benchmark improvement is quite reasonable in human's opinion.

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

Spiking CenterNet：一种用于目标检测的蒸馏增强脉冲神经网络

Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection

Fraunhofer IAIS（弗劳恩霍夫智能分析与信息系统研究所）；Fraunhofer IKS（弗劳恩霍夫认知系统研究所）；University of Bonn（波恩大学）

本文提出Spiking CenterNet，将脉冲神经网络CenterNet适配与M2U-Net解码器结合，用于事件数据目标检测，在GEN1数据集上以不到一半能耗显著超越已有方法，并首次在脉冲目标检测中引入知识蒸馏进一步提升性能。

2024-06-06cs.CVcs.LGcs.NE

面向遥感图像的通用知识增强预训练

Generic Knowledge Boosted Pre-training For Remote Sensing Images

State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）

提出 GeRSP 预训练框架，通过自监督遥感分支、监督自然图像分支及师生架构融合通用与领域知识，显著提升多项遥感下游任务性能。

2024-01-21cs.CV

EHGCN：基于运动感知GCN的分层欧氏-双曲融合的混合事件流感知方法

EHGCN: Hierarchical Euclidean-Hyperbolic Fusion via Motion-Aware GCN for Hybrid Event Stream Perception

提出首个联合欧氏与双曲空间建模的双空间事件感知方法EHGCN，通过多尺度体素事件筛选、MRF优化的运动感知超边生成及双空间GCN融合，在事件检测等任务中展现有效性。

2026-07-31cs.CV

PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks

Georgia State University（佐治亚州立大学）；Computer Science Department（计算机科学系）

Deep learning has gained great success in various classification tasks. Typically, deep learning models learn underlying features directly from data, and no underlying relationship between classes are included. Similarity between classes can influence the performance of classification. In this article, we propose a method that incorporates class similarity knowledge into convolutional neural networks models using a graph convolution layer. We evaluate our method on two benchmark image datasets: MNIST and CIFAR10, and analyze the results on different data and model sizes. Experimental results s…

2020-09-24cs.CVcs.LGeess.IV

基于两阶段蒸馏与渐进图神经网络的自粗到细人体姿态估计方法

A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network

Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University（教育部计算智能与中文信息处理重点实验室，计算机与信息技术学院，山西大学）

本文提出一种自粗到细的两阶段知识蒸馏人体姿态估计方法，通过人体关节结构损失和图像引导渐进图卷积网络，在保持轻量化的同时提升姿态估计精度，并在COCO和CrowdPose数据集上验证了其优越性。

2025-08-15cs.CV

Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

Harbin Institute of Technology（哈尔滨工业大学）；Tianjin University（天津大学）；Alibaba Group（阿里巴巴集团）；Pazhou Lab（琶洲实验室）

Weakly-supervised object detection (WSOD) has emerged as an inspiring recent topic to avoid expensive instance-level object annotations. However, the bounding boxes of most existing WSOD methods are mainly determined by precomputed proposals, thereby being limited in precise object localization. In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset. First, we use the well-annotated auxiliary dataset to explore a series of learnable bounding box adjusters (LBBAs) in a multi-…

2021-08-03cs.CV

更多相关论文收起更多论文

Distilling Knowledge from Graph Convolutional Networks

Stevens Institute of Technology（史蒂文斯理工学院）；The University of Sydney（悉尼大学）；Zhejiang University（浙江大学）

Existing knowledge distillation methods focus on convolutional neural networks (CNNs), where the input samples like images lie in a grid domain, and have largely overlooked graph convolutional networks (GCN) that handle non-grid data. In this paper, we propose to our best knowledge the first dedicated approach to distilling knowledge from a pre-trained GCN model. To enable the knowledge transfer from the teacher GCN to the student, we propose a local structure preserving module that explicitly accounts for the topological semantics of the teacher. In this module, the local structure informatio…

2021-01-10cs.CV

HOKEM：用于人-物交互检测的基于人体和物体关键点的扩展模块

HOKEM: Human and Object Keypoint-based Extension Module for Human-Object Interaction Detection

Hitachi, Ltd.（日立制作所）

本文提出HOKEM扩展模块，通过简单准确的物体关键点提取方法和引入自适应图优化与注意力机制的HO-AGCN，提升基于关键点的人-物交互检测精度，在V-COCO数据集上大幅提高了传统外观模型的准确率。

2023-06-25cs.CVcs.LG

MK-SGN：一种结合多模态融合与知识蒸馏的脉冲图卷积网络用于基于骨骼的动作识别

MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition

Beijing Laboratory of Advanced Information Networks, Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications（北京先进信息网络实验室、网络系统架构与收敛重点实验室、信息与通信工程学院、北京邮电大学）

针对基于GCN的骨骼动作识别方法能耗高的问题，首次提出结合多模态融合与知识蒸馏的脉冲图卷积网络MK-SGN，实现了98%以上的能耗降低，同时保持精度竞争力，为相关模型开发提供基线。

2025-11-19cs.CV

A New Channel Boosted Convolutional Neural Network using Transfer Learning

PIEAS（巴基斯坦工程与应用科学学院）；Center for Mathematical Sciences（数学科学中心）

We present a novel architectural enhancement of Channel Boosting in a deep convolutional neural network (CNN). This idea of Channel Boosting exploits both the channel dimension of CNN (learning from multiple input channels) and Transfer learning (TL). TL is utilized at two different stages; channel generation and channel exploitation. In the proposed methodology, a deep CNN is boosted by various channels available through TL from already trained Deep Neural Networks, in addition to its original channel. The deep architecture of CNN then exploits the original and boosted channels down the strea…

2020-07-04cs.CV

Video-based Facial Expression Recognition using Graph Convolutional Networks

Huazhong University of Science and Technology（华中科技大学）

Facial expression recognition (FER), aiming to classify the expression present in the facial image or video, has attracted a lot of research interests in the field of artificial intelligence and multimedia. In terms of video based FER task, it is sensible to capture the dynamic expression variation among the frames to recognize facial expression. However, existing methods directly utilize CNN-RNN or 3D CNN to extract the spatial-temporal features from different facial units, instead of concentrating on a certain region during expression variation capturing, which leads to limited performance i…

2020-10-26cs.CV

基于语言知识辅助表示学习的骨架动作识别

Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition

Xidian University（西安电子科技大学）；Alibaba Group（阿里巴巴集团）；Chongqing University of Posts and Telecommunications（重庆邮电大学）

本文提出LA-GCN图卷积网络，利用LLM知识构建先验全局关系和类别关系拓扑，结合多跳注意力图卷积加速收敛，在三个数据集上达到SOTA。

2023-05-21cs.CV

Multi-Label Classification with Label Graph Superimposing

Peking University（北京大学）；Baidu Inc.（百度公司）

Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep learning technologies. Recently, graph convolution network (GCN) is leveraged to boost the performance of multi-label recognition. However, what is the best way for label correlation modeling and how feature learning can be improved with label system awareness are still unclear. In this paper, we propose a label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recogni…

2019-11-21cs.CV

One-shot Scene Graph Generation

University of Electronic Science and Technology of China（电子科技大学）

As a structured representation of the image content, the visual scene graph (visual relationship) acts as a bridge between computer vision and natural language processing. Existing models on the scene graph generation task notoriously require tens or hundreds of labeled samples. By contrast, human beings can learn visual relationships from a few or even one example. Inspired by this, we design a task named One-Shot Scene Graph Generation, where each relationship triplet (e.g., "dog-has-head") comes from only one labeled example. The key insight is that rather than learning from scratch, one ca…

2022-02-26cs.CV

Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Grasping

Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）；Facebook AI Research（Facebook人工智能研究院）

Despite the enormous progress and generalization in robotic grasping in recent years, existing methods have yet to scale and generalize task-oriented grasping to the same extent. This is largely due to the scale of the datasets both in terms of the number of objects and tasks studied. We address these concerns with the TaskGrasp dataset which is more diverse both in terms of objects and tasks, and an order of magnitude larger than previous datasets. The dataset contains 250K task-oriented grasps for 56 tasks and 191 objects along with their RGB-D information. We take advantage of this new brea…

2020-11-13cs.CVcs.RO