Direct training high-performance spiking neural networks for object recognition and detection

Zhang, Hong; Li, Yang; He, Bin; Fan, Xiongfei; Wang, Yue; Zhang, Yu

doi:10.3389/fnins.2023.1229951

Cited by 7 publications

(3 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our RCFN is implemented in PyTorch with a single NVIDIA GeForce RTX 3090. We use Adadelta optimizer (Zeiler, 2012) with the learning rate increases from 0 to 1 at the first epoch and decays to 0 following the cosine schedules (Zhang et al, 2019b). No data augmentation for fair comparison.…”

Section: Implement Detailsmentioning

confidence: 99%

Language Model is Suitable for Correction of Handwritten Mathematical Expressions Recognition

Chen,

Han,

Yang

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Handwritten mathematical expression recognition (HMER) is a multidisciplinary task that generates LaTeX sequences from images. Existing approaches, employing tree decoders within attention-based encoder-decoder architectures, aim to capture the hierarchical tree structure, but are limited by CFGs and pregenerated triplet data, hindering expandability and neglecting visual ambiguity challenges. This article investigates the distinctive language characteristics of LaTeX mathematical expressions, revealing two key observations: 1) the presence of explicit structural symbols, and 2) the treatment of symbols as minimal units, each directly assigned specific semantics. Rooted in these properties, we propose that language models have the potential to synchronously and complementarily provide both structural and semantic information, making them suitable for correction of HMER. To validate our proposition, we propose an architecture called Recognition and Language Fusion Network (RLFN), which integrates recognition and language features to output corrected sequences while jointly optimizing with a string decoder recognition model. Experiments show that RLFN outperforms existing state-of-theart methods on the CROHME 2014/2016/2019 datasets. 1

show abstract

Section: Implement Detailsmentioning

confidence: 99%

Language Model is Suitable for Correction of Handwritten Mathematical Expressions Recognition

Chen,

Han,

Yang

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Spiking neural networks (SNNs) are frequently employed in numerous pixel-level classification tasks ( Martinez-Seras et al, 2023 ), such as object detection ( Zhang et al, 2023b ), image segmentation ( Zhang et al, 2023a ), and anomaly detection ( Yusob et al, 2018 ). Research centered on SNNs includes methods for neural network learning, data coding, and hardware platforms.…”

Section: Introductionmentioning

confidence: 99%

DCENet-based low-light image enhancement improved by spiking encoding and convLSTM

Wang,

Zhang

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

The direct utilization of low-light images hinders downstream visual tasks. Traditional low-light image enhancement (LLIE) methods, such as Retinex-based networks, require image pairs. A spiking-coding methodology called intensity-to-latency has been used to gradually acquire the structural characteristics of an image. convLSTM has been used to connect the features. This study introduces a simplified DCENet to achieve unsupervised LLIE as well as the spiking coding mode of a spiking neural network. It also applies the comprehensive coding features of convLSTM to improve the subjective and objective effects of LLIE. In the ablation experiment for the proposed structure, the convLSTM structure was replaced by a convolutional neural network, and the classical CBAM attention was introduced for comparison. Five objective evaluation metrics were compared with nine LLIE methods that currently exhibit strong comprehensive performance, with PSNR, SSIM, MSE, UQI, and VIFP exceeding the second place at 4.4% (0.8%), 3.9% (17.2%), 0% (15%), 0.1% (0.2%), and 4.3% (0.9%) on the LOL and SCIE datasets. Further experiments of the user study in five non-reference datasets were conducted to subjectively evaluate the effects depicted in the images. These experiments verified the remarkable performance of the proposed method.

show abstract

“…Spiking neural networks (SNNs) are frequently employed in numerous pixel-level classification tasks (Martinez-Seras et al, 2023), such as object detection (Zhang et al, 2023b), image segmentation (Zhang et al, 2023a), and anomaly detection (Yusob et al, 2018). Research centered on SNNs includes methods for neural network learning, data coding, and hardware platforms.…”

Section: Introductionmentioning

confidence: 99%

Advanced Methods and Applications for Neurointelligence

2024

Frontiers Research Topics

View full text Add to dashboard Cite

Frontiers is more than just an open access publisher of scholarly articles: it is a pioneering approach to the world of academia, radically improving the way scholarly research is managed. The grand vision of Frontiers is a world where all people have an equal opportunity to seek, share and generate knowledge. Frontiers provides immediate and permanent online open access to all its publications, but this alone is not enough to realize our grand goals. Frontiers journal seriesThe Frontiers journal series is a multi-tier and interdisciplinary set of openaccess, online journals, promising a paradigm shift from the current review, selection and dissemination processes in academic publishing. All Frontiers journals are driven by researchers for researchers; therefore, they constitute a service to the scholarly community. At the same time, the Frontiers journal series operates on a revolutionary invention, the tiered publishing system, initially addressing specific communities of scholars, and gradually climbing up to broader public understanding, thus serving the interests of the lay society, too. Dedication to qualityEach Frontiers article is a landmark of the highest quality, thanks to genuinely collaborative interactions between authors and review editors, who include some of the world's best academicians. Research must be certified by peers before entering a stream of knowledge that may eventually reach the public -and shape society; therefore, Frontiers only applies the most rigorous and unbiased reviews. Frontiers revolutionizes research publishing by freely delivering the most outstanding research, evaluated with no bias from both the academic and social point of view. By applying the most advanced information technologies, Frontiers is catapulting scholarly publishing into a new generation. What are Frontiers Research Topics?Frontiers Research Topics are very popular trademarks of the Frontiers journals series: they are collections of at least ten articles, all centered on a particular subject. With their unique mix of varied contributions from Original Research to Review Articles, Frontiers Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area.

show abstract

Direct training high-performance spiking neural networks for object recognition and detection

Cited by 7 publications

References 64 publications

Language Model is Suitable for Correction of Handwritten Mathematical Expressions Recognition

Language Model is Suitable for Correction of Handwritten Mathematical Expressions Recognition

DCENet-based low-light image enhancement improved by spiking encoding and convLSTM

Advanced Methods and Applications for Neurointelligence

Contact Info

Product

Resources

About