195 citations · 363 across the 10 of their papers we have counts for
11 papers
Scaling Vision Transformers to 22 Billion Parameters
Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…
CUF: Continuous Upsampling Filters
Cristina Vasconcelos, Cengiz Oztireli, Mark Matthews +3
Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we cons…
Proper Reuse of Image Classification Features Improves Object Detection
Cristina Vasconcelos, Vighnesh Birodkar, Vincent Dumoulin
A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature…
ConformalLayers: A non-linear sequential neural network with associative layers
Eduardo Vera Sousa, Leandro A. F. Fernandes, Cristina Nader Vasconcelos
Convolutional Neural Networks (CNNs) have been widely applied. But as the CNNs grow, the number of arithmetic operations and memory footprint also increase. Furthermore, typical no…
Spatially and color consistent environment lighting estimation using deep neural networks for mixed reality
Bruno Augusto Dorta Marques, Esteban Walter Gonzalez Clua, Anselmo Antunes Montenegro +1
The representation of consistent mixed reality (XR) environments requires adequate real and virtual illumination composition in real-time. Estimating the lighting of a real scenari…
Impact of Aliasing on Generalization in Deep Convolutional Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin +3
We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limi…