Zobrazeno 1 - 10
of 330
pro vyhledávání: '"Pedrini, Helio"'
Autor:
Moreira, Diego A. B., Ferreira, Alef Iury, Silva, Jhessica, Santos, Gabriel Oliveira dos, Pereira, Luiz, Gondim, João Medrado, Bonil, Gustavo, Maia, Helena, da Silva, Nádia, Hashiguti, Simone Tiemi, Santos, Jefersson A. dos, Pedrini, Helio, Avila, Sandra
Despite significant advancements and pervasive use of vision-language models, a paucity of studies has addressed their ethical implications. These models typically require extensive training data, often from hastily reviewed text and image datasets,
Externí odkaz:
http://arxiv.org/abs/2409.19474
Autor:
Lopes, Alexandre, Santos, Fernando Pereira dos, de Oliveira, Diulhio, Schiezaro, Mauricio, Pedrini, Helio
Publikováno v:
Computers & Graphics, Volume 123, October 2024, 104015
Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with
Externí odkaz:
http://arxiv.org/abs/2408.08250
This paper introduces a novel approach to improving the training stability of self-supervised learning (SSL) methods by leveraging a non-parametric memory of seen concepts. The proposed method involves augmenting a neural network with a memory compon
Externí odkaz:
http://arxiv.org/abs/2407.17486
Autor:
Santos, Gabriel Oliveira dos, Moreira, Diego A. B., Ferreira, Alef Iury, Silva, Jhessica, Pereira, Luiz, Bueno, Pedro, Sousa, Thiago, Maia, Helena, Da Silva, Nádia, Colombini, Esther, Pedrini, Helio, Avila, Sandra
This work introduces CAPIVARA, a cost-efficient framework designed to enhance the performance of multilingual CLIP models in low-resource languages. While CLIP has excelled in zero-shot vision-language tasks, the resource-intensive nature of model tr
Externí odkaz:
http://arxiv.org/abs/2310.13683
The intersection of vision and language is of major interest due to the increased focus on seamless integration between recognition and reasoning. Scene graphs (SGs) have emerged as a useful tool for multimodal image analysis, showing impressive perf
Externí odkaz:
http://arxiv.org/abs/2310.01842
Publikováno v:
4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop ICCV 2023
We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised convolutional-based method that learns representations suited for dense prediction tasks. CLoVE deviates from current methods and optimizes a single loss function that opera
Externí odkaz:
http://arxiv.org/abs/2310.00527
Weakly Supervised Semantic Segmentation (WSSS) techniques explore individual regularization strategies to refine Class Activation Maps (CAMs). In this work, we first analyze complementary WSSS techniques in the literature, their segmentation properti
Externí odkaz:
http://arxiv.org/abs/2305.12522
Early and accurate diagnosis of COVID-19 is essential to control the rapid spread of the pandemic and mitigate sequelae in the population. Current diagnostic methods, such as RT-PCR, are effective but require time to provide results and can quickly o
Externí odkaz:
http://arxiv.org/abs/2303.10738
Pruning is a standard technique for reducing the computational cost of deep networks. Many advances in pruning leverage concepts from the Lottery Ticket Hypothesis (LTH). LTH reveals that inside a trained dense network exists sparse subnetworks (tick
Externí odkaz:
http://arxiv.org/abs/2301.10835
Single image super-resolution (SISR) is the process of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the research community, due to the
Externí odkaz:
http://arxiv.org/abs/2210.03743