no code implementations • 3 May 2024 • Brayan Monroy, Juan Estupiñan, Tatiana Gelvez-Barrera, Jorge Bacca, Henry Arguello
Binary Neural Networks emerged as a cost-effective and energy-efficient solution for computer vision tasks by binarizing either network weights or activations.
1 code implementation • 8 Apr 2024 • Fabian Perez, Jhon Lopez, Henry Arguello
To address these challenges, we propose a novel Privacy-Preserving framework that uses a set of deformable operators for secure task learning.
1 code implementation • 1 Apr 2024 • Edwin Vargas, Claudia Correa, Carlos Hinojosa, Henry Arguello
In contrast to current BNN approaches, we propose to employ a binary periodic (BiPer) function during binarization.
Ranked #1 on Classification with Binary Neural Network on ImageNet (Top-1 metric)
no code implementations • 31 Mar 2024 • Jhon Lopez, Carlos Hinojosa, Henry Arguello, Bernard Ghanem
Specifically, our approach first learns an optical encoder along with a regression model to obtain a face heatmap while hiding the face identity from the source image.
no code implementations • 20 Oct 2023 • Roman Jacome, Kumar Vijay Mishra, Brian M. Sadler, Henry Arguello
The hypercomplex PR (HPR) arises in many optical imaging and computational sensing applications that usually comprise quaternion and octonion-valued signals.
no code implementations • 14 Sep 2023 • Jhon Lopez, Edwin Vargas, Henry Arguello
Depth estimation from a single image of a conventional camera is a challenging task since depth cues are lost during the acquisition process.
no code implementations • 30 Jul 2023 • Karen Sanchez, Carlos Hinojosa, Kevin Arias, Henry Arguello, Denis Kouame, Olivier Meyrignac, Adrian Basarab
This paper introduces a new data augmentation architecture that generates synthetic multiparametric (T1 arterial, T1 portal, and T2) magnetic resonance images (MRI) of massive macrotrabecular subtype hepatocellular carcinoma with their corresponding tumor masks through a generative deep learning approach.
2 code implementations • 29 Apr 2023 • Emmanuel Martinez, Roman Jacome, Alejandra Hernandez-Rojas, Henry Arguello
To surmount this limitation, we propose low-dimensional GAN (LD-GAN), where we train the GAN employing a low-dimensional representation of the {dataset} with the latent space of a pretrained autoencoder network.
no code implementations • 23 Mar 2023 • Roman Jacome, Edwin Vargas, Kumar Vijay Mishra, Brian M. Sadler, Henry Arguello
In these passive listening outposts, the signals and channels of both radar and communications are unknown to the receiver.
no code implementations • 21 Nov 2022 • Paul Goyes, Edwin Vargas, Claudia Correa, Yu Sun, Ulugbek Kamilov, Brendt Wohlberg, Henry Arguello
Physical and budget constraints often result in irregular sampling, which complicates accurate subsurface imaging.
no code implementations • 16 Nov 2022 • Jonathan Monsalve, Edwin Vargas, Kumar Vijay Mishra, Brian M. Sadler, Henry Arguello
In this dual-blind deconvolution (DBD) problem, the receiver admits a multi-carrier wireless communications signal that is overlaid with the radar signal reflected off multiple targets.
no code implementations • 5 Nov 2022 • Tatiana Gelvez-Barrera, Jorge Bacca, Henry Arguello
This paper proposes a non-data-driven deep neural network for spectral image recovery problems such as denoising, single hyperspectral image super-resolution, and compressive spectral imaging reconstruction.
no code implementations • 22 Sep 2022 • Emmanuel Martinez, Edwin Vargas, Henry Arguello
Specifically, we propose to jointly optimize an optical architecture for acquiring a single coded light field snapshot and a convolutional neural network (CNN) for estimating the disparity maps.
no code implementations • 27 Jun 2022 • Henry Arguello, Jorge Bacca, Hasindu Kariyawasam, Edwin Vargas, Miguel Marquez, Ramith Hettiarachchi, Hans Garcia, Kithmini Herath, Udith Haputhanthri, Balpreet Singh Ahluwalia, Peter So, Dushan N. Wadduwage, Chamira U. S. Edussooriya
The performance of COI systems highly depends on the design of its main components: the CE pattern and the computational method used to perform a given task.
no code implementations • 8 Jun 2022 • Carlos Hinojosa, Miguel Marquez, Henry Arguello, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles
The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition.
no code implementations • 27 May 2022 • Jorge Bacca, Alejandra Hernandez-Rojas, Henry Arguello
Compressive spectral imaging (CSI) has emerged as an attractive compression and sensing technique, primarily to sense spectral regions where traditional systems result in highly costly such as in the near-infrared spectrum.
no code implementations • 24 May 2022 • Roman Jacome, Jorge Bacca, Henry Arguello
To overcome this issue, compressive spectral image fusion (CSIF) employs the projected measurements of two CSI architectures with different resolutions to estimate a high-spatial high-spectral resolution.
1 code implementation • 16 May 2022 • Brayan Monroy, Jorge Bacca, Henry Arguello
Deep learning models are state-of-the-art in compressive spectral imaging (CSI) recovery.
no code implementations • 27 Jan 2022 • Samuel Pinilla, Kumar Vijay Mishra, Brian M. Sadler, Henry Arguello
The ability of a radar to discriminate in both range and Doppler velocity is completely characterized by the ambiguity function (AF) of its transmit waveform.
1 code implementation • IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) 2021 • Brayan Monroy, Jorge Bacca, Henry Arguello
This paper proposes an autoencoder-based network that guarantees a low-dimensional spectral representation through feature reduction, which can be used as prior in the compressive spectral imaging reconstruction.
no code implementations • 11 Nov 2021 • Edwin Vargas, Kumar Vijay Mishra, Roman Jacome, Brian M. Sadler, Henry Arguello
When the radar receiver is not collocated with the transmitter, such as in passive or multistatic radars, the transmitted signal is also unknown apart from the target parameters.
no code implementations • 14 Apr 2021 • Carlos Hinojosa, Esteban Vera, Henry Arguello
Accurate land cover segmentation of spectral images is challenging and has drawn widespread attention in remote sensing due to its inherent complexity.
no code implementations • ICCV 2021 • Edwin Vargas, Julien N. P. Martel, Gordon Wetzstein, Henry Arguello
Compressive imaging using coded apertures (CA) is a powerful technique that can be used to recover depth, light fields, hyperspectral images and other quantities from a single snapshot.
1 code implementation • 22 Feb 2021 • Juan Ramírez, Héctor Vargas, José Ignacio Martínez, Henry Arguello
In remote sensing, hyperspectral (HS) and multispectral (MS) image fusion have emerged as a synthesis tool to improve the data set resolution.
1 code implementation • 19 Jan 2021 • Jorge Bacca, Yesid Fonseca, Henry Arguello
The proposed method is based on the fact that the structure of some deep neural networks and an appropriated low-dimensional structure are sufficient to impose a structure of the underlying spectral image from CSI.
1 code implementation • 11 Jan 2021 • Jonathan Monsalve, Juan Ramirez, Iñaki Esnaola, Henry Arguello
The algorithm estimates the covariance matrix of hyperspectral images from synthetic and real compressive samples.
no code implementations • ICCV 2021 • Carlos Hinojosa, Juan Carlos Niebles, Henry Arguello
However, we also want the camera to capture useful information to perform computer vision tasks.
1 code implementation • 15 Sep 2020 • Juan Marcos Ramirez, Jose Ignacio Martinez-Torre, Henry Arguello
In this paper, a method that fuses features directly from multiresolution compressive measurements is proposed for spectral image classification.