Related papers: NFANet: A Novel Method for Weakly Supervised Water…

We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision. To do so we exploit depth and relative camera pose cues to…

Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task. In this paper, we propose to exploit an additional big dataset with different categories to improve the accuracy of few-shot…

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the…

Deep convolutional networks have achieved the state-of-the-art for semantic image segmentation tasks. However, training these networks requires access to densely labeled images, which are known to be very expensive to obtain. On the other…

Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

Neural networks in many varieties are touted as very powerful machine learning tools because of their ability to distill large amounts of information from different forms of data, extracting complex features and enabling powerful…

Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure.…

Monitoring coral reefs using underwater vehicles increases the range of marine surveys and availability of historical ecological data by collecting significant quantities of images. Analysis of this imagery can be automated using a model…

Underwater degraded images greatly challenge existing algorithms to detect objects of interest. Recently, researchers attempt to adopt attention mechanisms or composite connections for improving the feature representation of detectors.…

Pansharpening enhances spatial details of high spectral resolution multispectral images using features of high spatial resolution panchromatic image. There are a number of traditional pansharpening approaches but producing an image…

Most of the existing object detection methods generate poor glass detection results, due to the fact that the transparent glass shares the same appearance with arbitrary objects behind it in an image. Different from traditional deep…

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep…

Visual attributes play an essential role in real applications based on image retrieval. For instance, the extraction of attributes from images allows an eCommerce search engine to produce retrieval results with higher precision. The…

In the domain of computer vision, multi-scale feature extraction is vital for tasks such as salient object detection. However, achieving this capability in lightweight networks remains challenging due to the trade-off between efficiency and…

Footpath mapping, modeling, and analysis can provide important geospatial insights to many fields of study, including transport, health, environment and urban planning. The availability of robust Geographic Information System (GIS) layers…

Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN…

Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works…

With their combined spectral depth and geometric resolution, hyperspectral remote sensing images embed a wealth of complex, non-linear information that challenges traditional computer vision techniques. Yet, deep learning methods known for…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…