Relation Networks for Object Detection

Hu, Han; Gu, Jiwei; Zhang, Zheng; Dai, Jifeng; Wei, Yichen

doi:10.1109/cvpr.2018.00378

Cited by 1,316 publications

(855 citation statements)

References 61 publications

Supporting

Mentioning

854

Contrasting

Unclassified

Order By: Relevance

“…Object detection has attracted a great deal of attention in recent years [4,13,14,16,19,20,27,28,30,38,39,43,47,48,56]. One popular direction for recent object detection is proposal-based object detectors (a.k.a.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Tang

Wang

Bai

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

349

310

View full text Add to dashboard Cite

In this paper, we focus on semi-supervised object detection to boost accuracies of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train object detectors on unlabeled data due to the unavailability of ground truth labels. To address this problem, we present a proposal learning approach to learn proposal features and predictions from both labeled and unlabeled data. The approach consists of a self-supervised proposal learning module and a consistency-based proposal learning module. In the self-supervised proposal learning module, we present a proposal location loss and a contrastive loss to learn context-aware and noise-robust proposal features respectively. In the consistency-based proposal learning module, we apply consistency losses to both bounding box classification and regression predictions of proposals to learn noise-robust proposal features and predictions. Experiments are conducted on the COCO dataset with all available labeled and unlabeled data. Results show that our approach consistently improves the accuracies of fullysupervised baselines. In particular, after combining with data distillation [37], our approach improves AP by about 2.0% and 0.9% on average compared with fully-supervised baselines and data distillation baselines respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Previous works have shown that object detectors can benefit from context [2,7,19,33] and should be noiserobust [31,48]. Our self-supervised proposal learning module uses a proposal location loss and a contrastive loss to learn context-aware and noise-robust proposal features respectively.…”

Section: Self-supervised Proposal Learningmentioning

confidence: 99%

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Tang

Wang

Bai

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

349

310

View full text Add to dashboard Cite

show abstract

“…In the literature, there has been strong evidences on the use of object relation to support various vision tasks, e.g., recognition [48], object detection [17], cross-domain detection [2], and image captioning [52]. One representative work that employs object relation is [17] for object detection in images. The basic idea is to measure relation features of one object as the weighted sum of appearance features from other objects in the image and the weights reflect object dependency in terms of both appearance and geometry information.…”

Section: Introductionmentioning

confidence: 99%

Relation Distillation Networks for Video Object Detection

Deng

Pan

Yao

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

225

152

View full text Add to dashboard Cite

It has been well recognized that modeling object-toobject relations would be helpful for object detection. Nevertheless, the problem is not trivial especially when exploring the interactions between objects to boost video object detectors. The difficulty originates from the aspect that reliable object relations in a video should depend on not only the objects in the present frame but also all the supportive objects extracted over a long range span of the video. In this paper, we introduce a new design to capture the interactions across the objects in spatio-temporal context. Specifically, we present Relation Distillation Networks (RDN) -a new architecture that novelly aggregates and propagates object relation to augment object features for detection. Technically, object proposals are first generated via Region Proposal Networks (RPN). RDN then, on one hand, models object relation via multi-stage reasoning, and on the other, progressively distills relation through refining supportive object proposals with high objectness scores in a cascaded manner. The learnt relation verifies the efficacy on both improving object detection in each frame and box linking across frames. Extensive experiments are conducted on Im-ageNet VID dataset, and superior results are reported when comparing to state-of-the-art methods. More remarkably, our RDN achieves 81.8% and 83.2% mAP with ResNet-101 and ResNeXt-101, respectively. When further equipped with linking and rescoring, we obtain to-date the best reported mAP of 83.8% and 84.7%.

show abstract

“…, one can see even for the Nodule, which has a small lesion area, the network with the bottom‐up and top‐down structure performs better, this mainly because the large receptive field of view can extract more contextual information about disease. The contextual information around a lesion will be conducive to the diagnosis of disease, because if a lesion occurs in one location, nearby tissue will also change. In addition, we realized that the two structures that with and without bottom‐up and top‐down structures have almost the same performance for Fibrosis, in theory, the network with a large receptive field of view should have a significant improvement.…”

Section: Discussionmentioning

confidence: 99%

Dense networks with relative location awareness for thorax disease identification

et al. 2019

View full text Add to dashboard Cite

Purpose Chest X‐ray is one of the most common examinations for diagnosing heart and lung diseases. Due to the existing of a large number of clinical cases, many automated diagnosis algorithms based on chest X‐ray images have been proposed. To our knowledge, almost none of the previous auto‐diagnosis algorithms consider the effect of relative location information on disease incidence. In this study, we propose to use relative location information to assist the identification of thorax diseases. Method In this work, U‐Net is used to segment lung and heart from chest image. The relative location maps are computed through Euclidean distance transformation from segmented masks. By introducing the relative location information into the network, the usual location of disease is combined with the incidence. The proposed network is the fusion of two branches: mask branch and image branch. A mask branch is designed to be a bottom‐up and top‐down structure to extract relative location information. The structure has a large receptive field, which can extract more information for large lesion and contextual information for small lesion. The features learned from mask branch are fused with image branch, which is a 121‐layers DenseNet. Results We compare our proposed method with four state‐of‐the‐art methods on the largest public chest X‐ray dataset: ChestX‐ray14. The proposed method achieves the area under a curve of 0.820, which outperforms all the existing models and algorithms. Conclusion This paper proposed a dense network with relative location information to identify thorax disease. The method combines the usual location of disease with the incidence for the first time and performs good.

show abstract

Relation Networks for Object Detection

Cited by 1,316 publications

References 61 publications

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Relation Distillation Networks for Video Object Detection

Dense networks with relative location awareness for thorax disease identification

Contact Info

Product

Resources

About