On the applicability of the Hadamard as an input modulator for problems of classification

Curtò, J. de; Zarzà, I. de; Yan, Hong; Calafate, Carlos T.

doi:10.1016/j.simpa.2022.100325

Cited by 3 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…o W G r t P I 1 d Z 8 p w a t e 9 h f i a N 8 g x + T I s h M p y B M V f F i W 5 p K j p I j 4 6 F g Y 4 y r k j j B v h b q V 8 y g z j 6 E K u u h D C 9 Z c 3 S a / V D M + a p 9 9 O a x e t V R w V 8 o k c k z o J y T m 5 I J e k Q 7 q E k 1 / k N 3 k g j 9 6 t d + 8 9 e X 9 e W r e 8 1 c w R + Q / e 8 1 9 V Y q r G < / l a t e x i t > be important for future uses, allowing us to generalize them on other applications, or possibly other transforms [58]. RMSE and MAE Signature and log-signature can be used not only to compare models, but also to keep performance of training across several epochs, and analytically detect overfitting, as highlighted in Table III.…”

Section: X T E = " >mentioning

confidence: 99%

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

Curtò¹,

Zarzà²,

Hong³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

<p>In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization.</p>

show abstract

Section: X T E = " >mentioning

confidence: 99%

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

Curtò¹,

Zarzà²,

Hong³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent advances in Deep Neural Networks (DNN) [11][12][13] have spurred progress across various scientific fields [14][15][16][17][18][19][20][21]. In the realm of video summarization, two prominent approaches have emerged: LSTM-and RNN-based models [22][23][24].…”

Section: Introduction and Problem Statementmentioning

confidence: 99%

Summarization of Videos with the Signature Transform

et al. 2023

Self Cite

View full text Add to dashboard Cite

This manuscript presents a new benchmark for assessing the quality of visual summaries without the need for human annotators. It is based on the Signature Transform, specifically focusing on the RMSE and the MAE Signature and Log-Signature metrics, and builds upon the assumption that uniform random sampling can offer accurate summarization capabilities. We provide a new dataset comprising videos from Youtube and their corresponding automatic audio transcriptions. Firstly, we introduce a preliminary baseline for automatic video summarization, which has at its core a Vision Transformer, an image–text model pre-trained with Contrastive Language–Image Pre-training (CLIP), as well as a module of object detection. Following that, we propose an accurate technique grounded in the harmonic components captured by the Signature Transform, which delivers compelling accuracy. The analytical measures are extensively evaluated, and we conclude that they strongly correlate with the notion of a good summary.

show abstract