Quantitative, data-driven models for mental representations have long enjoyed popularity and success in psychology (e.g., distributional semantic models in the language domain), but have largely been missing for the visual domain. To overcome this, w...
Computational intelligence and neuroscience
Oct 6, 2022
Text classification plays an important role in many practical applications. In the real world, there are extremely small datasets. Most existing methods adopt pretrained neural network models to handle this kind of dataset. However, these methods are...
IEEE transactions on pattern analysis and machine intelligence
Oct 4, 2022
CNN-based salient object detection (SOD) methods achieve impressive performance. However, the way semantic information is encoded in them and whether they are category-agnostic is less explored. One major obstacle in studying these questions is the f...
IEEE transactions on pattern analysis and machine intelligence
Oct 4, 2022
Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bound...
The performance of deep learning-based medical image segmentation methods largely depends on the segmentation accuracy of tissue boundaries. However, since the boundary region is at the junction of areas of different categories, the pixels located at...
Representation learning seeks to extract useful and low-dimensional attributes from complex and high-dimensional data. Natural language processing (NLP) was used to investigate the representation learning models to extract words' feature vectors usin...
Low-level features contain spatial detail information, and high-level features contain rich semantic information. Semantic segmentation research focuses on fully acquiring and effectively fusing spatial detail with semantic information. This paper pr...
Revealing the function of uncharacterized genes is a fundamental challenge in an era of ever-increasing volumes of sequencing data. Here, we present a concept for tackling this challenge using deep learning methodologies adopted from natural language...
In general, most of the existing convolutional neural network (CNN)-based deep-learning models suffer from spatial-information loss and inadequate feature-representation issues. This is due to their inability to capture multiscale-context information...