Related papers: UPANets: Learning from the Universal Pixel Attenti…
It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…
Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…
Convolutional Neural Networks (CNNs) have advanced existing medical systems for automatic disease diagnosis. However, there are still concerns about the reliability of deep medical diagnosis systems against the potential threats of…
Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be…
This paper is on highly accurate and highly efficient human pose estimation. Recent works based on Fully Convolutional Networks (FCNs) have demonstrated excellent results for this difficult problem. While residual connections within FCNs…
Deep learning has made significant progress in computer vision, specifically in image classification, object detection, and semantic segmentation. The skip connection has played an essential role in the architecture of deep neural…
We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…
Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechanisms based on self-attention leads to improved performance on…
Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional Unet architectures and their transformer-integrated variants excel in automated segmentation tasks. However, they lack…
The encode-decoder framework has shown recent success in image captioning. Visual attention, which is good at detailedness, and semantic attention, which is good at comprehensiveness, have been separately proposed to ground the caption on…
We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature vector maps which form the intermediate representations of the…
Skip connections are central to U-Net architectures for image denoising, but standard concatenation doubles channel dimensionality and obscures information flow, allowing uncontrolled noise transfer. We propose the Additive U-Net, which…
Accurate medical image segmentation is an integral part of the medical image analysis pipeline that requires the ability to merge local and global information. While vision transformers are able to capture global interactions using vanilla…
In recent years, significant advancements have been made in deep learning for medical image segmentation, particularly with convolutional neural networks (CNNs) and transformer models. However, CNNs face limitations in capturing long-range…
Since their emergence, Convolutional Neural Networks (CNNs) have made significant strides in medical image analysis. However, the local nature of the convolution operator may pose a limitation for capturing global and long-range…
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can…
Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the "double attention…
We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing spatial and temporal pooling,…
Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is often unavailable due to computational constraints. To address…
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…