Multi-Head-Self-Attention based YOLOv5X-transformer for multi-scale object detection

Vasanthi, Ponduri; Mohan, Laavanya

doi:10.1007/s11042-023-15773-4

Cited by 8 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Mosaic data augmentation [10] technique is a popular approach used to augment training data in the proposed model. Mosaic data augmentation combines four randomly selected images from the dataset into a single mosaic image, which is then used for training.…”

Section: Data Augmentationmentioning

confidence: 99%

Extreme small-scale prediction head-based efficient YOLOV5 for small-scale object detection

Gowthami,

Blessy

2024

Eng. Res. Express

View full text Add to dashboard Cite

Recognition models achieved exceptional performance in object detection during the computer vision era, but they still rely on Small-Scale Object Detection (SSOD). SSOD remains difficult due to the variety of shapes and orientations of the object, as well as fixed prediction heads at the detection stage. To overcome these challenges, our paper proposed an auto anchor module, Spatial Pyramid Pooling Faster layer (SPPF) in the feature refinement network, and an extremely small-scale prediction head at the detection stage of the model. With the auto anchor feature, the model is able to adjust the anchor boxes dynamically during training, which can improve its overall performance. The SPPF layer divides the feature map into five levels of pyramids, where each level corresponds to a different scale. This enables the model to detect objects of different sizes by pooling features from all the levels of the pyramid. Extreme Small Scale prediction head is specifically designed for small object detection and uses anchor boxes with small sizes and feature re-sampling techniques to improve the accuracy of SSOD. We perform quantitative evaluations on the VOC and achieved 85.4 mAP, 79.8% precision, 80.3% recall, and 80% F1-score. These reliable results prove that the suggested model has greater performance compared with existing models in detecting small-scale objects.

show abstract

Section: Data Augmentationmentioning

confidence: 99%

Extreme small-scale prediction head-based efficient YOLOV5 for small-scale object detection

Gowthami,

Blessy

2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

GEL-TTA Net: a Global ensemble learning network for the localization of small-scale and mixed intracranial hemorrhages through test time augmentations

Kothala,

Guntur

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Generative artificial intelligence: a systematic review and applications

Sengar,

Hasan,

Kumar

et al. 2024

Multimed Tools Appl

View full text Add to dashboard Cite

In recent years, the study of artificial intelligence (AI) has undergone a paradigm shift. This has been propelled by the groundbreaking capabilities of generative models both in supervised and unsupervised learning scenarios. Generative AI has shown state-of-the-art performance in solving perplexing real-world conundrums in fields such as image translation, medical diagnostics, textual imagery fusion, natural language processing, and beyond. This paper documents the systematic review and analysis of recent advancements and techniques in Generative AI with a detailed discussion of their applications including application-specific models. Indeed, the major impact that generative AI has made to date, has been in language generation with the development of large language models, in the field of image translation and several other interdisciplinary applications of generative AI. Moreover, the primary contribution of this paper lies in its coherent synthesis of the latest advancements in these areas, seamlessly weaving together contemporary breakthroughs in the field. Particularly, how it shares an exploration of the future trajectory for generative AI. In conclusion, the paper ends with a discussion of Responsible AI principles, and the necessary ethical considerations for the sustainability and growth of these generative models.

show abstract

Multi-Head-Self-Attention based YOLOv5X-transformer for multi-scale object detection

Cited by 8 publications

References 33 publications

Extreme small-scale prediction head-based efficient YOLOV5 for small-scale object detection

Extreme small-scale prediction head-based efficient YOLOV5 for small-scale object detection

GEL-TTA Net: a Global ensemble learning network for the localization of small-scale and mixed intracranial hemorrhages through test time augmentations

Generative artificial intelligence: a systematic review and applications

Contact Info

Product

Resources

About