Related papers: Top-down Neural Attention by Excitation Backprop
Sampling-based motion planning is an effective tool to compute safe trajectories for automated vehicles in complex environments. However, a fast convergence to the optimal solution can only be ensured with the use of problem-specific…
We here propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs).…
Deep neural nets typically perform end-to-end backpropagation to learn the weights, a procedure that creates synchronization constraints in the weight update step across layers and is not biologically plausible. Recent advances in…
A major advantage of a deep convolutional neural network (CNN) is that the focused receptive field size is increased by stacking multiple convolutional layers. Accordingly, the model can explore the long-range dependency of features from…
Recent successes in image analysis with deep neural networks are achieved almost exclusively with Convolutional Neural Networks (CNNs), typically trained using the backpropagation (BP) algorithm. In a 2022 preprint, Geoffrey Hinton proposed…
Previous studies suggested that lateral interactions of V1 cells are responsible, among other visual effects, of bottom-up visual attention (alternatively named visual salience or saliency). Our objective is to mimic these connections with…
Many visual phenomena suggest that humans use top-down generative or reconstructive processes to create visual percepts (e.g., imagery, object completion, pareidolia), but little is known about the role reconstruction plays in robust object…
Recently Convolutional Neural Networks (CNNs) have been shown to achieve state-of-the-art performance on various classification tasks. In this paper, we present for the first time a place recognition technique based on CNN models, by…
Deep convolutional neural networks (CNN) have revolutionized various fields of vision research and have seen unprecedented adoption for multiple tasks such as classification, detection, captioning, etc. However, they offer little…
Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-attention layers to obtain a…
Convolutional neural networks are basic structures using jet images as input for the jet tagging problems. However, what they have learned during the training process is always difficult to understand just through feature maps. Inspired by…
This paper proposes a new topology optimization method that applies a convolutional neural network (CNN), which is one deep learning technique for topology optimization problems. Using this method, we acquire a structure with a little…
Leveraging the advanced functionalities of modern radio frequency (RF) modeling and simulation tools, specifically designed for adaptive radar processing applications, this paper presents a data-driven approach to improve accuracy in radar…
Convolution Neural Networks (CNN) have been extremely successful in solving intensive computer vision tasks. The convolutional filters used in CNNs have played a major role in this success, by extracting useful features from the inputs.…
Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such models can be enhanced by guiding a randomly initialized model…
The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains. Most such models use multi-head self-attention which is appealing for the ability to attend to…
We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task…
We propose here an extended attention model for sequence-to-sequence recurrent neural networks (RNNs) designed to capture (pseudo-)periods in time series. This extended attention model can be deployed on top of any RNN and is shown to yield…
In this paper, we present a Neuron Abandoning Attention Flow (NAFlow) method to address the open problem of visually explaining the attention evolution dynamics inside CNNs when making their classification decisions. A novel cascading…
Top-performing landmark estimation algorithms are based on exploiting the excellent ability of large convolutional neural networks (CNNs) to represent local appearance. However, it is well known that they can only learn weak spatial…