Selfreg: Regularization Method via High-level Feature

Person re-identification (ReID) plays a significant role in video surveillance analysis. In the real world, due to illumination, occlusion, and deformation, pedestrian features extraction is the key to person ReID. Considering the shortcomings of existing methods in pedestrian features extraction, a method based on attention mechanism and context information fusion is proposed. A lightweight attention module is introduced into ResNet50 backbone network equipped with a small number of network parameters, which enhance the significant characteristics of person and suppress irrelevant information. Aiming at the problem of person context information loss due to the over depth of the network, a context information fusion module is designed to sample the shallow feature map of pedestrians and cascade with the high-level feature map. In order to improve the robustness, the model is trained by combining the loss of margin sample mining with the loss function of cross entropy. Experiments are carried out on datasets Market1501 and DukeMTMC-reID, our method achieves rank-1 accuracy of 95.9% on the Market1501 dataset, and 90.1% on the DukeMTMC-reID dataset, outperforming the current mainstream method in case of only using global feature.

Download Full-text

Deep AI Enabled Ubiquitous Wireless Sensing

ACM Computing Surveys ◽

10.1145/3436729 ◽

2021 ◽

Vol 54 (2) ◽

pp. 1-35

Author(s):

Chenning Li ◽

Zhichao Cao ◽

Yunhao Liu

Keyword(s):

Great Success ◽

Wireless Sensing ◽

Ubiquitous Sensing ◽

Sensing Systems ◽

The Status ◽

Sensing Model ◽

High Level ◽

Traditional Approaches ◽

The Internet Of Things ◽

High Level Feature

With the development of the Internet of Things (IoT), many kinds of wireless signals (e.g., Wi-Fi, LoRa, RFID) are filling our living and working spaces nowadays. Beyond communication, wireless signals can sense the status of surrounding objects, known as wireless sensing , with their reflection, scattering, and refraction while propagating in space. In the last decade, many sophisticated wireless sensing techniques and systems were widely studied for various applications (e.g., gesture recognition, localization, and object imaging). Recently, deep Artificial Intelligence (AI), also known as Deep Learning (DL), has shown great success in computer vision. And some works have initially proved that deep AI can benefit wireless sensing as well, leading to a brand-new step toward ubiquitous sensing. In this survey, we focus on the evolution of wireless sensing enhanced by deep AI techniques. We first present a general workflow of Wireless Sensing Systems (WSSs) which consists of signal pre-processing, high-level feature, and sensing model formulation. For each module, existing deep AI-based techniques are summarized, further compared with traditional approaches. Then, we provide a view of issues and challenges induced by combining deep AI and wireless sensing together. Finally, we discuss the future trends of deep AI to enable ubiquitous wireless sensing.

Download Full-text

Insulators Recognition Based on Enhancement of High-Level Feature with Improved Attention Method

10.1109/phm-nanjing52125.2021.9613029 ◽

2021 ◽

Author(s):

Yixiao Li ◽

Honghao Liu ◽

Huan Wang ◽

Zhiliang Liu

Keyword(s):

High Level ◽

High Level Feature

Download Full-text

Multimodal Remote Sensing Image Classification with Small Sample Size Based on High-Level Feature Fusion

Laser & Optoelectronics Progress ◽

10.3788/lop56.111001 ◽

2019 ◽

Vol 56 (11) ◽

pp. 111001

Author(s):

贺琪 Qi He ◽

李瑶 Yao Li ◽

宋巍 Wei Song ◽

黄冬梅 Dongmei Huang ◽

何盛琪 Shengqi He ◽

...

Keyword(s):

Remote Sensing ◽

Sample Size ◽

Image Classification ◽

Feature Fusion ◽

Small Sample Size ◽

Remote Sensing Image ◽

Small Sample ◽

Remote Sensing Image Classification ◽

High Level ◽

High Level Feature

Download Full-text

Domain Conditioned Adaptation Network

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6801 ◽

2020 ◽

Vol 34 (07) ◽

pp. 11386-11393 ◽

Cited By ~ 1

Author(s):

Shuang Li ◽

Chi Liu ◽

Qiuxia Lin ◽

Binhui Xie ◽

Zhengming Ding ◽

...

Keyword(s):

Domain Adaptation ◽

Feature Learning ◽

Feature Representations ◽

Domain Specific ◽

Cross Domain ◽

Learning Tasks ◽

Domain Learning ◽

High Level ◽

High Level Feature ◽

Target Data

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target. However, we argue that such strongly-shared convolutional layers might be harmful for domain-specific feature learning when source and target data distribution differs to a large extent. In this paper, we relax a shared-convnets assumption made by previous DA methods and propose a Domain Conditioned Adaptation Network (DCAN), which aims to excite distinct convolutional channels with a domain conditioned channel attention mechanism. As a result, the critical low-level domain-dependent knowledge could be explored appropriately. As far as we know, this is the first work to explore the domain-wise convolutional channel activation for deep DA networks. Moreover, to effectively align high-level feature distributions across two domains, we further deploy domain conditioned feature correction blocks after task-specific layers, which will explicitly correct the domain discrepancy. Extensive experiments on three cross-domain benchmarks demonstrate the proposed approach outperforms existing methods by a large margin, especially on very tough cross-domain learning tasks.

Download Full-text