Spatial-Aware Graph Relation Network for Large-Scale Object Detection

Xu, Hang; Jiang, Chonghe; Liang, Xiaodan; Li, Zhenguo

doi:10.1109/cvpr.2019.00952

Cited by 128 publications

(69 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Significant progress has been made in recent years on FSOD task using CNN. Modern CNN based FSOD methods may be categorized in two groups: one-stage detection methods such as SSD and YOLO Redmon et al 2016a; and two-stage detection methods such as Faster R-CNN and R-FCN ( Dai et al;Xu et al 2016;2015a;2019b;2019a). Although these methods have achieved satisfactoring detection results, the requirement of large-scale bounding-box annotations may hinder their usage in some budget-aware scenarios.…”

Section: Related Workmentioning

confidence: 99%

EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement

Fang

Liu

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detectors have much lower performance and cannot be used reliably in a realistic setting. In this paper, we study the hybrid-supervised object detection problem, aiming to train a high quality detector with only a limited amount of fully-annotated data and fully exploiting cheap data with image-level labels. State of the art methods typically propose an iterative approach, alternating between generating pseudo-labels and updating a detector. This paradigm requires careful manual hyper-parameter tuning for mining good pseudo labels at each round and is quite time-consuming. To address these issues, we present EHSOD, an end-to-end hybrid-supervised object detection system which can be trained in one shot on both fully and weakly-annotated data. Specifically, based on a two-stage detector, we proposed two modules to fully utilize the information from both kinds of labels: 1) CAM-RPN module aims at finding foreground proposals guided by a class activation heat-map; 2) hybrid-supervised cascade module further refines the bounding-box position and classification with the help of an auxiliary head compatible with image-level data. Extensive experiments demonstrate the effectiveness of the proposed method and it achieves comparable results on multiple object detection benchmarks with only 30% fully-annotated data, e.g. 37.5% mAP on COCO. We will release the code and the trained models.

show abstract

Section: Related Workmentioning

confidence: 99%

EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement

Fang

Liu

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [33], object features are enhanced via attending different semantic concepts and propagating information through a common sense knowledge graph. In [32], a sparse graph is built based on semantic and spatial relations among objects. Our work is closely related to them while we focus on the relations between diseases and structures.…”

Section: Object Detection/instance Segmentationmentioning

confidence: 99%

A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation

Lian

Liu

Zhang

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Instance level detection and segmentation of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images. Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN. The SAR-Net consists of three relation modules: 1. the anatomical structure relation module encoding spatial relations between diseases and anatomical parts. 2. the contextual relation module aggregating clues based on query-key pair of disease RoI and lung fields. 3. the disease relation module propagating co-occurrence and causal relations into disease proposals. Towards making a practical system, we also provide ChestX-Det, a chest X-Ray dataset with instance-level annotations (boxes and masks). ChestX-Det is a subset of the public dataset NIH ChestX-ray14. It contains ∼ 3500 images of 13 common disease categories labeled by three board-certified radiologists. We evaluate our SAR-Net on it and another dataset DR-Private. Experimental results show that it can enhance the strong baseline of Mask R-CNN with significant improvements. The ChestX-Det is released at

show abstract

“…X.H. used the spatial-aware graph relation network to model important semantic and spatial relation between objects 24 . A spatial relation reasoning framework was to developed to encode object features 25 .…”

Section: Object Detection With Contextual Relationmentioning

confidence: 99%

Real-time Factory Smoke Detection Based on Two-stage Relation-guided Algorithm

Wang

Yin

2021

Preprint

View full text Add to dashboard Cite

Recently, using image sensing devices to analyze air quality has attracted much attention of researchers. To keep real-time factory smoke under universal social supervision, this paper proposes a mobile-platform-running efficient smoke detection algorithm based on image analysis techniques. Since most smoke images in real scenes have challenging variances, it’s difficult for existing object detection methods. To this end, we introduce the two-stage smoke detection (TSSD) algorithm based on the lightweight framework, in which the prior knowledge and contextual information are modeled into the relation-guided module to reduce the smoke search space, which can therefore significantly improve the shortcomings of the single-stage method. Experimental results show that the TSSD algorithm can robustly improve the detection accuracy of the single-stage method and has good compatibility for different image resolution inputs. Compared with various state-of-the-art detection methods, the accuracy AP mean of the TSSD model reaches 59.24%, even surpassing the current detection model Faster R-CNN. In addition, the detection speed of our proposed model can reach 50 ms (20 FPS), which meets the real-time requirements, and can be deployed in the mobile terminal carrier. This model can be widely used in some scenes with smoke detection requirements, providing great potential for practical environmental applications.

show abstract

Spatial-Aware Graph Relation Network for Large-Scale Object Detection

Cited by 128 publications

References 31 publications

EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement

EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement

A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation

Real-time Factory Smoke Detection Based on Two-stage Relation-guided Algorithm

Contact Info

Product

Resources

About