scholarly journals One-Shot Texture Retrieval with Global Context Metric

2019 ◽  
Author(s):  
Kai Zhu ◽  
Wei Zhai ◽  
Zheng-Jun Zha ◽  
Yang Cao
Keyword(s):  
Texture Segmentation ◽  
Context Information ◽  
Invariant Representation ◽  
Query Image ◽  
Reference Category ◽  
Channel Modulation ◽  
Global Context ◽  
Gating Mechanism ◽  
Local Relation ◽  
Texture Retrieval

In this paper, we tackle one-shot texture retrieval: given an example of a new reference texture, detect and segment all the pixels of the same texture category within an arbitrary image. To address this problem, we present an OS-TR network to encoding both reference patch and query image, leading to achieve texture segmentation towards the reference category. Unlike the existing texture encoding methods that integrate CNN with orderless pooling, we propose a directionality-aware network to capture the texture variations at each direction, resulting in spatially invariant representation. To segment new categories given only few examples, we incorporate a self-gating mechanism into relation network to exploit global context information for adjusting per-channel modulation weights of local relation features. Extensive experiments on benchmark texture datasets and real scenarios demonstrate the above-par segmentation performance and robust generalization across domains of our proposed method.

scholarly journals HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images

2020 ◽  
Vol 13 (1) ◽  
pp. 71
Author(s):  
Zhiyong Xu ◽  
Weicun Zhang ◽  
Tianxiang Zhang ◽  
Jiangyun Li
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
High Resolution ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
Context Information ◽  
Remote Sensing Images ◽  
Global Context ◽  
Boundary Information ◽  
Extraction Stage

Semantic segmentation is a significant method in remote sensing image (RSIs) processing and has been widely used in various applications. Conventional convolutional neural network (CNN)-based semantic segmentation methods are likely to lose the spatial information in the feature extraction stage and usually pay little attention to global context information. Moreover, the imbalance of category scale and uncertain boundary information meanwhile exists in RSIs, which also brings a challenging problem to the semantic segmentation task. To overcome these problems, a high-resolution context extraction network (HRCNet) based on a high-resolution network (HRNet) is proposed in this paper. In this approach, the HRNet structure is adopted to keep the spatial information. Moreover, the light-weight dual attention (LDA) module is designed to obtain global context information in the feature extraction stage and the feature enhancement feature pyramid (FEFP) structure is promoted and employed to fuse the contextual information of different scales. In addition, to achieve the boundary information, we design the boundary aware (BA) module combined with the boundary aware loss (BAloss) function. The experimental results evaluated on Potsdam and Vaihingen datasets show that the proposed approach can significantly improve the boundary and segmentation performance up to 92.0% and 92.3% on overall accuracy scores, respectively. As a consequence, it is envisaged that the proposed HRCNet model will be an advantage in remote sensing images segmentation.

scholarly journals Devil in the Details: Towards Accurate Single and Multiple Human Parsing

2019 ◽  
Vol 33 ◽  
pp. 4814-4821 ◽  
Author(s):  
Tao Ruan ◽  
Ting Liu ◽  
Zilong Huang ◽  
Yunchao Wei ◽  
Shikui Wei ◽  
...  
Keyword(s):  
The State ◽  
Future Research ◽  
Context Information ◽  
Global Context ◽  
The Arts ◽  
End To End ◽  
Feature Resolution

Human parsing has received considerable interest due to its wide application potentials. Nevertheless, it is still unclear how to develop an accurate human parsing system in an efficient and elegant way. In this paper, we identify several useful properties, including feature resolution, global context information and edge details, and perform rigorous analyses to reveal how to leverage them to benefit the human parsing task. The advantages of these useful properties finally result in a simple yet effective Context Embedding with Edge Perceiving (CE2P) framework for single human parsing. Our CE2P is end-to-end trainable and can be easily adopted for conducting multiple human parsing. Benefiting the superiority of CE2P, we won the 1st places on all three human parsing tracks in the 2nd Look into Person (LIP) Challenge. Without any bells and whistles, we achieved 56.50% (mIoU), 45.31% (mean APr) and 33.34% (APp0.5) in Track 1, Track 2 and Track 5, which outperform the state-of-the-arts more than 2.06%, 3.81% and 1.87%, respectively. We hope our CE2P will serve as a solid baseline and help ease future research in single/multiple human parsing. Code has been made available at https://github.com/liutinglt/CE2P.

scholarly journals Occluded Pedestrian Detection Techniques by Deformable Attention-Guided Network (DAGN)

2021 ◽  
Vol 11 (13) ◽  
pp. 6025
Author(s):  
Han Xie ◽  
Wenqi Zheng ◽  
Hyunchul Shin
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Pedestrian Detection ◽  
Tone Mapping ◽  
Context Information ◽  
Global Context ◽  
Detection Techniques ◽  
Low Visibility ◽  
Bounding Boxes ◽  
Preprocessing Technique

Although many deep-learning-based methods have achieved considerable detection performance for pedestrians with high visibility, their overall performances are still far from satisfactory, especially when heavily occluded instances are included. In this research, we have developed a novel pedestrian detector using a deformable attention-guided network (DAGN). Considering that pedestrians may be deformed with occlusions or under diverse poses, we have designed a deformable convolution with an attention module (DCAM) to sample from non-rigid locations, and obtained the attention feature map by aggregating global context information. Furthermore, the loss function was optimized to get accurate detection bounding boxes, by adopting complete-IoU loss for regression, and the distance IoU-NMS was used to refine the predicted boxes. Finally, a preprocessing technique based on tone mapping was applied to cope with the low visibility cases due to poor illumination. Extensive evaluations were conducted on three popular traffic datasets. Our method could decrease the log-average miss rate (MR−2) by 12.44% and 7.8%, respectively, for the heavy occlusion and overall cases, when compared to the published state-of-the-art results of the Caltech pedestrian dataset. Of the CityPersons and EuroCity Persons datasets, our proposed method outperformed the current best results by about 5% in MR−2 for the heavy occlusion cases.

scholarly journals An Iterative Polishing Framework Based on Quality Aware Masked Language Model for Chinese Poetry Generation

2020 ◽  
Vol 34 (05) ◽  
pp. 7643-7650
Author(s):  
Liming Deng ◽  
Jie Wang ◽  
Hangming Liang ◽  
Hui Chen ◽  
Zhiqiang Xie ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Language Model ◽  
Automatic Generation ◽  
Context Information ◽  
Chinese Poetry ◽  
Model Structure ◽  
Automatic Evaluation ◽  
Highly Qualified ◽  
Polishing Process ◽  
Global Context

Owing to its unique literal and aesthetical characteristics, automatic generation of Chinese poetry is still challenging in Artificial Intelligence, which can hardly be straightforwardly realized by end-to-end methods. In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation. In the first stage, an encoder-decoder structure is utilized to generate a poem draft. Afterwards, our proposed Quality-Aware Masked Language Model (QA-MLM) is employed to polish the draft towards higher quality in terms of linguistics and literalness. Based on a multi-task learning scheme, QA-MLM is able to determine whether polishing is needed based on the poem draft. Furthermore, QA-MLM is able to localize improper characters of the poem draft and substitute with newly predicted ones accordingly. Benefited from the masked language model structure, QA-MLM incorporates global context information into the polishing process, which can obtain more appropriate polishing results than the unidirectional sequential decoding. Moreover, the iterative polishing process will be terminated automatically when QA-MLM regards the processed poem as a qualified one. Both human and automatic evaluation have been conducted, and the results demonstrate that our approach is effective to improve the performance of encoder-decoder structure.

Object detector with enriched global context information

2020 ◽  
Vol 79 (39-40) ◽  
pp. 29551-29571
Author(s):  
Jingjuan Guo ◽  
Caihong Yuan ◽  
Zhiqiang Zhao ◽  
Ping Feng ◽  
Yihao Luo ◽  
...  
Keyword(s):  
Context Information ◽  
Global Context

Cervical cell multi-classification algorithm using global context information and attention mechanism

2022 ◽  
Vol 74 ◽  
pp. 101677
Author(s):  
Jun Li ◽  
Qiyan Dou ◽  
Haima Yang ◽  
Jin Liu ◽  
Le Fu ◽  
...  
Keyword(s):  
Classification Algorithm ◽  
Attention Mechanism ◽  
Context Information ◽  
Global Context ◽  
Cervical Cell ◽  
Multi Classification

Prime Proportion Affects Masked Priming of Fixed and Free-Choice Responses

2010 ◽  
Vol 57 (5) ◽  
pp. 360-366 ◽  
Author(s):  
Glen E. Bodner ◽  
Rehman Mulji
Keyword(s):  
Decision Process ◽  
Free Choice ◽  
Masked Priming ◽  
Local Context ◽  
Previous Trial ◽  
Target Response ◽  
Global Context ◽  
Sequential Trial

Left/right “fixed” responses to arrow targets are influenced by whether a masked arrow prime is congruent or incongruent with the required target response. Left/right “free-choice” responses on trials with ambiguous targets that are mixed among fixed trials are also influenced by masked arrow primes. We show that the magnitude of masked priming of both fixed and free-choice responses is greater when the proportion of fixed trials with congruent primes is .8 rather than .2. Unconscious manipulation of context can thus influence both fixed and free choices. Sequential trial analyses revealed that these effects of the overall prime context on fixed and free-choice priming can be modulated by the local context (i.e., the nature of the previous trial). Our results support accounts of masked priming that posit a memory-recruitment, activation, or decision process that is sensitive to aspects of both the local and global context.

Sign in / Sign up

Export Citation Format

Share Document