From Face Images and Attributes to Attributes

Torfason, Robert; Agustsson, Eirikur; Rothe, Rasmus; Timofte, Radu

doi:10.1007/978-3-319-54187-7_21

Cited by 16 publications

(14 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LNet [19] 85.00 LNet+ANet [1] 87.00 CNN+SVM [20] 89.80 ft +Color+LBP+SIFT [21] 90.22 MobileNetV2 [22] 91.00…”

Section: Methods Accuracymentioning

confidence: 99%

“…Firmino et al [18] used automatic and semi-automatic annotation techniques for people in photos using the shared event concept, which consists of many photos captured by different devices of people who attended the same event. Among the most popular and efficient approaches for facial image annotation are various convolutional neural networks (CNNs) [1,[19][20][21][22].…”

Section: Face Attribute Prediction and Annotationmentioning

confidence: 99%

See 1 more Smart Citation

A Method for Human Facial Image Annotation on Low Power Consumption Autonomous Devices

Hachaj

2020

Sensors

View full text Add to dashboard Cite

This paper proposes a classifier designed for human facial feature annotation, which is capable of running on relatively cheap, low power consumption autonomous microcomputer systems. An autonomous system is one that depends only on locally available hardware and software—for example, it does not use remote services available through the Internet. The proposed solution, which consists of a Histogram of Oriented Gradients (HOG) face detector and a set of neural networks, has comparable average accuracy and average true positive and true negative ratio to state-of-the-art deep neural network (DNN) architectures. However, contrary to DNNs, it is possible to easily implement the proposed method in a microcomputer with very limited RAM memory and without the use of additional coprocessors. The proposed method was trained and evaluated on a large 200,000 image face data set and compared with results obtained by other researchers. Further evaluation proves that it is possible to perform facial image attribute classification using the proposed algorithm on incoming video data captured by an RGB camera sensor of the microcomputer. The obtained results can be easily reproduced, as both the data set and source code can be downloaded. Developing and evaluating the proposed facial image annotation algorithm and its implementation, which is easily portable between various hardware and operating systems (virtually the same code works both on high-end PCs and microcomputers using the Windows and Linux platforms) and which is dedicated for low power consumption devices without coprocessors, is the main and novel contribution of this research.

show abstract

“…LNet [19] 85.00 LNet+ANet [1] 87.00 CNN+SVM [20] 89.80 ft +Color+LBP+SIFT [21] 90.22 MobileNetV2 [22] 91.00…”

Section: Methods Accuracymentioning

confidence: 99%

Section: Face Attribute Prediction and Annotationmentioning

confidence: 99%

A Method for Human Facial Image Annotation on Low Power Consumption Autonomous Devices

Hachaj

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…For the CelebA dataset, we consider the identification as the privacy component, and the gender and smiling recognition as the two downstream tasks used the model in [27], [28]. As shown in Figure 6, the OCTOPUS model can reduce the test accuracy of private information (identification) from 85% down to around 10% on average, demonstrating the ability to protect private information.…”

Section: Effect On Privacymentioning

confidence: 99%

OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning

Wang,

Nepal,

Moore

et al. 2021

Preprint

View full text Add to dashboard Cite

The diversity and quantity of the data warehousing, gathering data from distributed devices such as mobile phones, can enhance machine learning algorithms' success and robustness. Federated learning enables distributed participants to collaboratively learn a commonly-shared model while holding data locally. However, it is also faced with expensive communication and limitations due to the heterogeneity of distributed data sources and lack of access to global data. In this paper, we investigate a practical distributed learning scenario where multiple downstream tasks (e.g., classifiers) could be learned from dynamically-updated and non-iid distributed data sources, efficiently and providing local privatization. We introduce a new distributed learning scheme to address communication overhead via latent compression, leveraging global data while providing local privatization of local data without additional cost due to encryption or perturbation. This scheme divides the learning into (1) informative feature encoding, extracting and transmitting the latent space compressed representation features of local data at each node to address communication overhead; (2) downstream tasks centralized at the server using the encoded codes gathered from each node to address computing and storage overhead. Besides, a disentanglement strategy is applied to address the privatization of sensitive components of local data. Extensive experiments are conducted on image and speech datasets. The results demonstrate that downstream tasks on the compact latent representations can achieve comparable accuracy to centralized learning with the privatization of local data.

show abstract

“…Several previous works [2], [3], [18]- [20] indicate that there are unfairness issues in existing image datasets. [3] shows that most benchmark datasets for face recognition are biased to Caucasians than other ethnicities and proposes Pilot Parliament Benchmark (PPB) dataset that is balanced for skin color and gender [21], [22].…”

Section: Related Work a Fairness In Computer Visionmentioning

confidence: 99%

“…[3] shows that most benchmark datasets for face recognition are biased to Caucasians than other ethnicities and proposes Pilot Parliament Benchmark (PPB) dataset that is balanced for skin color and gender [21], [22]. Furthermore, [18]- [20] claims sensitive attributes, such as gender, age, and ethnicity, are correlated with specific facial attributes in CelebA and UTK Face datasets [23], [24]. Similarly, [25] finds out that some gender-stereotyped objects are frequently co-occurred with a specific gender (i.e.,male or female) in MS-COCO dataset [26].…”

Section: Related Work a Fairness In Computer Visionmentioning

confidence: 99%

Fair-VQA: Fairness-Aware Visual Question Answering Through Sensitive Attribute Prediction

et al. 2020

View full text Add to dashboard Cite

Visual Question Answering (VQA) is a task that answers questions on given images. Although previous works achieve a great improvement in VQA performance, they do not consider the fairness of answers in terms of ethically sensitive attributes, such as gender. Therefore, we propose a Fair-VQA model that contains two modules: VQA module and SAP (Sensitive Attribute Prediction) module. On top of VQA module, which predicts various kinds of answers, SAP module predicts only sensitive attributes using the same inputs. The predictions of SAP module are utilized to rectify answers from VQA module to be fairer in terms of the sensitive attributes with graceful performance degradation. To validate the proposed method, we conduct extensive experiments on VQA, GQA, and our proposing VQA-Gender datasets. In all the experiments, our method shows the fairest results in various metrics for fairness. Moreover, we demonstrate that our method works interpretably through the analysis of visualized attention maps.

show abstract

From Face Images and Attributes to Attributes

Cited by 16 publications

References 35 publications

A Method for Human Facial Image Annotation on Low Power Consumption Autonomous Devices

A Method for Human Facial Image Annotation on Low Power Consumption Autonomous Devices

OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning

Fair-VQA: Fairness-Aware Visual Question Answering Through Sensitive Attribute Prediction

Contact Info

Product

Resources

About