Related papers: Squeeze aggregated excitation network
Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the…
Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…
Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are…
Saliency prediction can benefit from training that involves scene understanding that may be tangential to the central task; this may include understanding places, spatial layout, objects or involve different datasets and their bias. One can…
Medical image segmentation has been very challenging due to the large variation of anatomy across different cases. Recent advances in deep learning frameworks have exhibited faster and more accurate performance in image segmentation. Among…
Deep learning surrogate models are being increasingly used in accelerating scientific simulations as a replacement for costly conventional numerical techniques. However, their use remains a significant challenge when dealing with real-world…
The spread of deepfakes poses significant security concerns, demanding reliable detection methods. However, diverse generation techniques and class imbalance in datasets create challenges. We propose CAE-Net, a Convolution- and…
Attributed network embedding (ANE) is to learn low-dimensional vectors so that not only the network structure but also node attributes can be preserved in the embedding space. Existing ANE models do not consider the specific combination…
Existing subset selection methods for efficient learning predominantly employ discrete combinatorial and model-specific approaches which lack generalizability. For an unseen architecture, one cannot use the subset chosen for a different…
Convolutional Neural Networks (CNN) increase depth by stacking convolutional layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolutional layers does not make the network…
Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters…
Accelerating the deep learning inference is very important for real-time applications. In this paper, we propose a novel method to fuse the layers of convolutional neural networks (CNNs) on Graphics Processing Units (GPUs), which applies…
Different from the general visual classification, some classification tasks are more challenging as they need the professional categories of the images. In the paper, we call them expert-level classification. Previous fine-grained vision…
Humans can infer approximate interaction force between objects from only vision information because we already have learned it through experiences. Based on this idea, we propose a recurrent convolutional neural network-based method using…
The emergence of ConvNeXt and its variants has reaffirmed the conceptual and structural suitability of CNN-based models for vision tasks, re-establishing them as key players in image classification in general, and in facial expression…
Graph embedding is gaining its popularity for link prediction in complex networks and achieving excellent performance. However, limited work has been done in sparse networks that represent most of real networks. In this paper, we propose a…
This paper presents a module, Spatial Cross-scale Convolution (SCSC), which is verified to be effective in improving both CNNs and Transformers. Nowadays, CNNs and Transformers have been successful in a variety of tasks. Especially for…
In this paper we investigate the amount of spatial context required for channel attention. To this end we study the popular squeeze-and-excite (SE) block which is a simple and lightweight channel attention mechanism. SE blocks and its…
The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…
This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a…