Related papers: Momentum Auxiliary Network for Supervised Local Le…
Deep neural networks are typically trained using global error signals that backpropagate (BP) end-to-end, which is not only biologically implausible but also suffers from the update locking problem and requires huge memory consumption.…
Real-time semantic segmentation, which aims to achieve high segmentation accuracy at real-time inference speed, has received substantial attention over the past few years. However, many state-of-the-art real-time semantic segmentation…
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint. This paper aims to address this problem by revisiting the locally…
The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its…
In recent years, single image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) have made significant progress. However, due to the non-adaptive nature of the convolution operation, they cannot adapt to…
Memory-Augmented Neural Networks (MANNs) are a class of neural networks equipped with an external memory, and are reported to be effective for tasks requiring a large long-term memory and its selective use. The core module of a MANN is…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by learning directly from image input. A deep neural network is used as a function approximator and requires no specific state information.…
End-to-end training with full-depth backpropagation remains the dominant paradigm for optimizing deep neural networks, but its efficiency deteriorates as models grow deeper. Since every block must be executed and differentiated under a…
Traditional deep network training methods optimize a monolithic objective function jointly for all the components. This can lead to various inefficiencies in terms of potential parallelization. Local learning is an approach to…
Efficient on-device Convolutional Neural Network (CNN) training in resource-constrained mobile and edge environments is an open challenge. Backpropagation is the standard approach adopted, but it is GPU memory intensive due to its strong…
Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention…
Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradient to update model parameters, which becomes time-consuming…
Skeleton-based action recognition task is entangled with complex spatio-temporal variations of skeleton joints, and remains challenging for Recurrent Neural Networks (RNNs). In this work, we propose a temporal-then-spatial recalibration…
This work studies the class of algorithms for learning with side-information that emerge by extending generative models with embedded context-related variables. Using finite mixture models (FMM) as the prototypical Bayesian network, we show…
The vast majority of modern deep learning models are trained with momentum-based first-order optimizers. The momentum term governs the optimizer's memory by determining how much each past gradient contributes to the current convergence…
Hyperspectral image denoising is unique for the highly similar and correlated spectral information that should be properly considered. However, existing methods show limitations in exploring the spectral correlations across different bands…
The process of training a deep neural network is characterized by significant time requirements and associated costs. Although researchers have made considerable progress in this area, further work is still required due to resource…
Mixture-of-Experts (MoE) has emerged as a promising approach to scale up deep learning models due to its significant reduction in computational resources. However, the dynamic nature of MoE leads to load imbalance among experts, severely…
The performance of existing supervised neuron segmentation methods is highly dependent on the number of accurate annotations, especially when applied to large scale electron microscopy (EM) data. By extracting semantic information from…
Momentum based optimizers are central to a wide range of machine learning applications. These typically rely on an Exponential Moving Average (EMA) of gradients, which decays exponentially the present contribution of older gradients. This…