Related papers: Evolving Normalization-Activation Layers
An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network. Despite the astonishing performance, deep features extracted from low-level…
Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary…
Biological nervous systems consist of networks of diverse, sophisticated information processors in the form of neurons of different classes. In most artificial neural networks (ANNs), neural computation is abstracted to an activation…
In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with…
We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then…
We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic tasks. Our generic tasks…
As the deep neural networks are being applied to complex tasks, the size of the networks and architecture increases and their topology becomes more complicated too. At the same time, training becomes slow and at some instances inefficient.…
Dense prediction tasks typically employ encoder-decoder architectures, but the prevalent convolutions in the decoder are not image-adaptive and can lead to boundary artifacts. Different generalized convolution operations have been…
This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective…
A Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node representations over graph-structured data. Though powerful, GCNs…
In this work, we propose a novel activation mechanism called LayerAct for CNNs. This approach is motivated by our theoretical and experimental analyses, which demonstrate that Layer Normalization (LN) can mitigate a limitation of existing…
Deep neural networks are ubiquitous due to the ease of developing models and their influence on other domains. At the heart of this progress is convolutional neural networks (CNNs) that are capable of learning representations or features…
Graph Neural Networks (GNNs) have attracted considerable attention and have emerged as a new promising paradigm to process graph-structured data. GNNs are usually stacked to multiple layers and the node representations in each layer are…
The presence of noise is common in signal processing regardless the signal type. Deep neural networks have shown good performance in noise removal, especially on the image domain. In this work, we consider deep neural networks as a…
The process of aggregation is ubiquitous in almost all deep nets models. It functions as an important mechanism for consolidating deep features into a more compact representation, whilst increasing robustness to overfitting and providing…
Understanding the operation of biological and artificial networks remains a difficult and important challenge. To identify general principles, researchers are increasingly interested in surveying large collections of networks that are…
Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and address it by manually designing kinds of regularization terms and data terms of the latent clear images. However,…
In this paper, we jointly combine image classification and image denoising, aiming to enhance human perception of noisy images captured by edge devices, like low-light security cameras. In such settings, it is important to retain the…
We show that existing upsampling operators can be unified using the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can often recover…
Deep neural networks are a promising approach towards multi-task learning because of their capability to leverage knowledge across domains and learn general purpose representations. Nevertheless, they can fail to live up to these promises…