Accurate localization for mobile device using a multi-planar city model

Luo, Yawei; Guan, Tao; Pan, Hailong; Wang, Yuesong; Yu, Jiguo

doi:10.1109/icpr.2016.7900215

Cited by 5 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural network has been widely used in object detection and localization tasks [16,22,23,24,25,26]. One of the earliest deep networks to detect objects in a one-stage manner is OverFeat [27], which employs a multiscale and sliding window approach to predict object boundaries.…”

Section: Related Workmentioning

confidence: 99%

Self-produced Guidance for Weakly-Supervised Object Localization

Zhang

Wei

Kang

et al. 2018

Lecture Notes in Computer Science

192

205

View full text Add to dashboard Cite

Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discriminative parts of the object which are small and sparse. We propose to generate Self-produced Guidance (SPG) masks which separate the foreground i.e., the object of interest, from the background to provide the classification networks with spatial correlation information of pixels. A stagewise approach is proposed to incorporate high confident object regions to learn the SPG masks. The high confident regions within attention maps are utilized to progressively learn the SPG masks. The masks are then used as an auxiliary pixel-level supervision to facilitate the training of classification networks. Extensive experiments on ILSVRC demonstrate that SPG is effective in producing high-quality object localizations maps. Particularly, the proposed SPG achieves the Top-1 localization error rate of 43.83% on the ILSVRC validation set, which is a new state-of-the-art error rate.

show abstract

Section: Related Workmentioning

confidence: 99%

Self-produced Guidance for Weakly-Supervised Object Localization

Zhang

Wei

Kang

et al. 2018

Lecture Notes in Computer Science

192

205

View full text Add to dashboard Cite

show abstract

“…Served as a post-process procedure for image segmentation, CRFs further fine-tune the output map. However, the most common used CRFs are with pair-wise potentials [2,26], which has very limited parameters and handles low-level inconsistencies with a small scope. Higher-order potentials [16,18] have also been observed to be effective in enforcing the semantic validity, but the corresponding energy pattern and the clique form are usually difficult to design.…”

Section: Related Workmentioning

confidence: 99%

Macro-Micro Adversarial Network for Human Parsing

Luo

Zheng

et al. 2018

Lecture Notes in Computer Science

Self Cite

127

View full text Add to dashboard Cite

In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two discriminators. One discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU=46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at https://github.com/RoyalVane/MMAN.

show abstract

Unsupervised Domain Adaptive Image Semantic Segmentation Based on Convolutional Fine-Grained Discriminant and Entropy Minimization

Zhao

Lan

2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Accurate localization for mobile device using a multi-planar city model

Cited by 5 publications

References 19 publications

Self-produced Guidance for Weakly-Supervised Object Localization

Self-produced Guidance for Weakly-Supervised Object Localization

Macro-Micro Adversarial Network for Human Parsing

Unsupervised Domain Adaptive Image Semantic Segmentation Based on Convolutional Fine-Grained Discriminant and Entropy Minimization

Contact Info

Product

Resources

About