Image Polarity Detection on Resource-Constrained Devices

Ragusa, Edoardo; Gianoglio, Christian; Zunino, Rodolfo; Gastaldo, Paolo

doi:10.1109/mis.2020.3011586

Cited by 13 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MobilenetV1 is about 32 times lighter in terms of memory usage, and performs 27 times more efficiently in terms of floating-point operations. Nonetheless, MobileNetV1 attains a comparable accuracy in polarity detection [13].…”

Section: Image Classifiermentioning

confidence: 97%

“…The deployment of image polarity classifiers on resourceconstrained devices seems to have drawn a limited attention. In [13], the authors analyzed solutions including hardwarefriendly neural networks and weight truncation, but considered quite expensive hardware accelerators for deep learning. By contrast, this paper targets standard microprocessors and extends that research by including automatic saliency detection, to the purpose of further enhancing visual-polarity assessment.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, Ragusa et al [13] showed that, in the presence of a large dataset for fine-tuning, one can implement polarity detection by means of hardware-friendly CNNs without compromising the eventual generalization performances. Those results were achieved by means of MobileNetV1, an architecture specifically designed for embedded systems.…”

Section: Object Classificationmentioning

confidence: 99%

“…This is crucial for polarity detection [10][11][12], since the salient parts of an image carry relevant information for sentiment analysis, too. In spite of these promising features, CNNs cannot usually fit the constraints imposed by smart devices [13].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Design and Deployment of an Image Polarity Detector with Visual Attention

et al. 2021

Self Cite

View full text Add to dashboard Cite

Embedding the ability of sentiment analysis in smart devices is especially challenging because sentiment analysis relies on deep neural networks, in particular, convolutional neural networks. The paper presents a novel hardware-friendly detector of image polarity, enhanced with the ability of saliency detection. The approach stems from a hardware-oriented design process, which trades off prediction accuracy and computational resources. The eventual solution combines lightweight deep-learning architectures and post-training quantization. Experimental results on standard benchmarks confirmed that the design strategy can infer automatically the salient parts and the polarity of an image with high accuracy. Saliency-based solutions in the literature prove impractical due to their considerable computational costs; the paper shows that the novel design strategy can deploy and perform successfully on a variety of commercial smartphones, yielding real-time performances.

show abstract

Section: Image Classifiermentioning

confidence: 97%

Section: Related Workmentioning

confidence: 99%

Section: Object Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Design and Deployment of an Image Polarity Detector with Visual Attention

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The recent growth of industrial applications for object detection stimulates the research community toward novel solutions. Intelligent video analysis is the core of several industry applications such as transportation [ 1 ], sentiment analysis [ 2 ], and sport [ 3 , 4 ].…”

Section: Introductionmentioning

confidence: 99%

T-RexNet—A Hardware-Aware Neural Network for Real-Time Detection of Small Moving Objects

Canepa

Ragusa

Zunino

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents the T-RexNet approach to detect small moving objects in videos by using a deep neural network. T-RexNet combines the advantages of Single-Shot-Detectors with a specific feature-extraction network, thus overcoming the known shortcomings of Single-Shot-Detectors in detecting small objects. The deep convolutional neural network includes two parallel paths: the first path processes both the original picture, in gray-scale format, and differences between consecutive frames; in the second path, differences between a set of three consecutive frames is only handled. As compared with generic object detectors, the method limits the depth of the convolutional network to make it less sensible to high-level features and easier to train on small objects. The simple, Hardware-efficient architecture attains its highest accuracy in the presence of videos with static framing. Deploying our architecture on the NVIDIA Jetson Nano edge-device shows its suitability to embedded systems. To prove the effectiveness and general applicability of the approach, real-world tests assessed the method performances in different scenarios, namely, aerial surveillance with the WPAFB 2009 dataset, civilian surveillance using the Chinese University of Hong Kong (CUHK) Square dataset, and fast tennis-ball tracking, involving a custom dataset. Experimental results prove that T-RexNet is a valid, general solution to detect small moving objects, which outperforms in this task generic existing object-detection approaches. The method also compares favourably with application-specific approaches in terms of the accuracy vs. speed trade-off.

show abstract