Related papers: Studying inductive biases in image classification …
3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…
This work leverages the recent advancements of deep learning in image processing to find optimal locations that present the important characteristics of a field. The data for training are collected at different fields in local farms with…
Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…
Since scenes are composed in part of objects, accurate recognition of scenes requires knowledge about both scenes and objects. In this paper we address two related problems: 1) scale induced dataset bias in multi-scale convolutional neural…
Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level…
Brain extraction or whole brain segmentation is an important first step in many of the neuroimage analysis pipelines. The accuracy and robustness of brain extraction, therefore, is crucial for the accuracy of the entire brain analysis…
Presenting whole slide images (WSIs) as graph will enable a more efficient and accurate learning framework for cancer diagnosis. Due to the fact that a single WSI consists of billions of pixels and there is a lack of vast annotated datasets…
Deep learning has been widely adopted for channel state information (CSI)-fingerprinting indoor localization systems. These systems usually consist of two main parts, i.e., a positioning network that learns the mapping from high-dimensional…
Convolutional Neural Networks (CNNs) have recently been shown to excel at performing visual place recognition under changing appearance and viewpoint. Previously, place recognition has been improved by intelligently selecting relevant…
In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of this is that a filter may know what it is…
As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes. In contrast to some previous works utilizing…
The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks. However, existing methods often struggle to effectively utilize…
The current models of image representation based on Convolutional Neural Networks (CNN) have shown tremendous performance in image retrieval. Such models are inspired by the information flow along the visual pathway in the human visual…
Self-attention (SA) mechanisms can capture effectively global dependencies in deep neural networks, and have been applied to natural language processing and image processing successfully. However, SA modules for image reconstruction have…
Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution traverses the input images/features using a sliding window scheme to…
Objects, in the real world, rarely occur in isolation and exhibit typical arrangements governed by their independent utility, and their expected interaction with humans and other objects in the context. For example, a chair is expected near…
Recent developments in Transformers for language modeling have opened new areas of research in computer vision. Results from late 2019 showed vast performance increases in both object detection and recognition when convolutions are replaced…
Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information.…
Convolutional Neural Networks (CNNs) have been the standard for image classification tasks for a long time, but more recently attention-based mechanisms have gained traction. This project aims to compare traditional CNNs with…
Deep Convolutional Neural Network (CNN) features have been demonstrated to be effective perceptual quality features. The perceptual loss, based on feature maps of pre-trained CNN's has proven to be remarkably effective for CNN based…