scholarly journals SAL-Net: Self-Supervised Attribute Learning for Object Recognition and Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Shu Yang ◽  
JingWang ◽  
Sheeraz Arif ◽  
Minli Jia ◽  
Shunan Zhong
Keyword(s):  
Object Recognition ◽  
Image Classification ◽  
Semantic Segmentation ◽  
Experimental Results ◽  
Loss Functions ◽  
Learning Methods ◽  
Object Region ◽  
Triplet Loss ◽  
Attribute Learning ◽  
The Relationship

Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, which automatically generates attribute descriptions by differentially occluding the object region to deal with the above problems. The relationship between attributes is formulated with triplet loss functions and is utilized to supervise the CNN. Attribute learning is used as an auxiliary task of a multitask image classification and segmentation network, in which self-supervision of attributes motivates the CNN to learn more discriminative features for the main semantic tasks. Experimental results on public benchmarks CUB-2011 and Pascal VOC show that the proposed SAL-Net can obtain more accurate classification and segmentation results without additional annotations. Moreover, the SAL-Net is embedded into a multiobject recognition and segmentation system, which realizes instance-aware semantic segmentation with the help of a region proposal algorithm and a fusion nonmaximum suppression algorithm.

Parasites and promiscuity: Acute disease salience leads to more restricted sexual attitudes

2021 ◽  
pp. 026540752110309
Author(s):  
James B. Moran ◽  
Nicholas Kerry ◽  
Jin X. Goh ◽  
Damian R. Murray
Keyword(s):  
Social Behavior ◽  
Sexual Attitudes ◽  
Experimental Manipulation ◽  
Sexual Relationships ◽  
Experimental Results ◽  
Acute Disease ◽  
Short Term ◽  
Attitudes And Behaviors ◽  
The Relationship ◽  
Sexual Promiscuity

How does disease threat influence sexual attitudes and behaviors? Although research on the influence of disease threat on social behavior has grown considerably, the relationship between perceived disease threat and sexual attitudes remains unclear. The current preregistered study (analyzed N = 510), investigated how experimental reminders of disease threat influence attitudes and anticipated future behaviors pertaining to short-term sexual relationships, using an ecologically valid disease prime. The central preregistered prediction was that experimental manipulation of disease threat would lead to less favorable attitudes and inclinations toward sexual promiscuity. Results were consistent with this preregistered prediction, relative to both a neutral control condition and a non-disease threat condition. These experimental results were buttressed by the finding that dispositional variation in worry about disease threat predicted less favorable attitudes and inclinations toward short-term sexual relationships. This study represents the first preregistered investigation of the implications of acute disease threat for sexual attitudes.

scholarly journals Deep Learning Based Pavement Inspection Using Self-Reconfigurable Robot

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2595
Author(s):  
Balakrishnan Ramalingam ◽  
Abdullah Aamir Hayat ◽  
Mohan Rajesh Elara ◽  
Braulio Félix Gómez ◽  
Lim Yi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Semantic Segmentation ◽  
High Accuracy ◽  
Experimental Results ◽  
Mobile Mapping ◽  
Mapping System ◽  
Mobile Mapping System ◽  
Reconfigurable Robot ◽  
Nvidia Gpu ◽  
Inspection Task

The pavement inspection task, which mainly includes crack and garbage detection, is essential and carried out frequently. The human-based or dedicated system approach for inspection can be easily carried out by integrating with the pavement sweeping machines. This work proposes a deep learning-based pavement inspection framework for self-reconfigurable robot named Panthera. Semantic segmentation framework SegNet was adopted to segment the pavement region from other objects. Deep Convolutional Neural Network (DCNN) based object detection is used to detect and localize pavement defects and garbage. Furthermore, Mobile Mapping System (MMS) was adopted for the geotagging of the defects. The proposed system was implemented and tested with the Panthera robot having NVIDIA GPU cards. The experimental results showed that the proposed technique identifies the pavement defects and litters or garbage detection with high accuracy. The experimental results on the crack and garbage detection are presented. It is found that the proposed technique is suitable for deployment in real-time for garbage detection and, eventually, sweeping or cleaning tasks.

Research on Paper Whiteness Based on Visual Comfort

2013 ◽  
Vol 295-298 ◽  
pp. 543-546
Author(s):  
Zhi Jian Li ◽  
Nuo Li
Keyword(s):  
Negative Impact ◽  
Experimental Results ◽  
Reading Process ◽  
Visual Comfort ◽  
Visual Fatigue ◽  
The Relationship

High whiteness paper is likely to cause visual fatigue. The relationship between whiteness and visual comfort is studyed by adopting the form of a combination of presentation reading and questionnaires. The experimental results show that, during the reading process, the higher of paper whiteness, the greater the chance of looked up, eye rubbing, and other little tricks, at the same time, the easier inattentive, have a negative impact on reading effect.

scholarly journals Characterization of percolation behavior in conductor–dielectric 0-3 composites

2014 ◽  
Vol 04 (04) ◽  
pp. 1450035 ◽  
Author(s):  
Lin Zhang ◽  
Patrick Bass ◽  
Zhi-Min Dang ◽  
Z.-Y. Cheng
Keyword(s):  
Dielectric Constant ◽  
Percolation Threshold ◽  
Frequency Dependence ◽  
Experimental Results ◽  
Effective Dielectric Constant ◽  
Filler Concentration ◽  
Percolation Behavior ◽  
The Matrix ◽  
The Relationship

The equation ε eff ∝ (ϕc - ϕ)-s which shows the relationship between effective dielectric constant (εeff) and the filler concentration (φ), is widely used to determine the percolation behavior and obtain parameters, such as percolation threshold φc and the power constant s in conductor–dielectric composites (CDCs). Six different systems of CDCs were used to check the expression by fitting experimental results. It is found that the equation can fit the experimental results at any frequency. However, it is found that the fitting constants do not reflect the real percolation behavior of the composites. It is found that the dielectric constant is strongly dependent on the frequency, which is mainly due to the fact that the frequency dependence of the dielectric constant for the composites close to φc is almost independent of the matrix.

Face Recognition Algorithm Based on Kernel Collaborative Representation

2013 ◽  
Vol 756-759 ◽  
pp. 3590-3595
Author(s):  
Liang Zhang ◽  
Ji Wen Dong
Keyword(s):  
Face Recognition ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Recognition Algorithm ◽  
Experimental Results ◽  
Collaborative Representation ◽  
Nonlinear Structures ◽  
Components Analysis ◽  
Kernel Principal Components Analysis ◽  
The Relationship

Aiming at solving the problems of occlusion and illumination in face recognition, a new method of face recognition based on Kernel Principal Components Analysis (KPCA) and Collaborative Representation Classifier (CRC) is developed. The KPCA can obtain effective discriminative information and reduce the feature dimensions by extracting faces nonlinear structures features, the decisive factor. Considering the collaboration among the samples, the CRC which synthetically consider the relationship among samples is used. Experimental results demonstrate that the algorithm obtains good recognition rates and also improves the efficiency. The KCRC algorithm can effectively solve the problem of illumination and occlusion in face recognition.

Sign in / Sign up

Export Citation Format

Share Document