Efficient visual recognition: A survey on recent advances and brain-inspired methodologies
Visual recognition is currently one of the most important and active research areas in
computer vision, pattern recognition, and even the general field of artificial intelligence. It …
computer vision, pattern recognition, and even the general field of artificial intelligence. It …
Fire detection in video surveillances using convolutional neural networks and wavelet transform
Fire is one of the most frequent and common emergencies threatening public safety and
social development. Recently, intelligent fire detection technologies represented by …
social development. Recently, intelligent fire detection technologies represented by …
Decoupled greedy learning of cnns
E Belilovsky, M Eickenberg… - … Conference on Machine …, 2020 - proceedings.mlr.press
A commonly cited inefficiency of neural network training by back-propagation is the update
locking problem: each layer must wait for the signal to propagate through the network before …
locking problem: each layer must wait for the signal to propagate through the network before …
Online learned continual compression with adaptive quantization modules
We introduce and study the problem of Online Continual Compression, where one attempts
to simultaneously learn to compress and store a representative dataset from a non iid data …
to simultaneously learn to compress and store a representative dataset from a non iid data …
Joint time–frequency scattering
In time series classification and regression, signals are typically mapped into some
intermediate representation used for constructing models. Since the underlying task is often …
intermediate representation used for constructing models. Since the underlying task is often …
Compressed vision for efficient video understanding
O Wiles, J Carreira, I Barr… - Proceedings of the …, 2022 - openaccess.thecvf.com
Experience and reasoning occur across multiple temporal scales: milliseconds, seconds,
hours or days. The vast majority of computer vision research, however, still focuses on …
hours or days. The vast majority of computer vision research, however, still focuses on …
[HTML][HTML] Harmonic convolutional networks based on discrete cosine transform
Convolutional neural networks (CNNs) learn filters in order to capture local correlation
patterns in feature space. We propose to learn these filters as combinations of preset …
patterns in feature space. We propose to learn these filters as combinations of preset …
Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets
In this article, we propose a set of transform-based neural network layers as an alternative to
the 3 x 3 Conv2D layers in convolutional neural networks (CNNs). The proposed layers can …
the 3 x 3 Conv2D layers in convolutional neural networks (CNNs). The proposed layers can …
Harmonic networks for image classification
Convolutional neural networks (CNNs) learn filters in order to capture local correlation
patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce …
patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce …
DCT perceptron layer: A transform domain approach for convolution layer
In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network
layer which we call DCT-perceptron to replace the $3\times3 $ Conv2D layers in the …
layer which we call DCT-perceptron to replace the $3\times3 $ Conv2D layers in the …