Related papers: NFANet: A Novel Method for Weakly Supervised Water…
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing…
Methods that combine local and global features have recently shown excellent performance on multiple challenging deep image retrieval benchmarks, but their use of local features raises at least two issues. First, these local features simply…
Objective: To automatically create large labeled training datasets and reduce the efforts of feature engineering for training accurate machine learning models for clinical information extraction. Materials and Methods: We propose a distant…
Automatic road extraction from satellite imagery using deep learning is a viable alternative to traditional manual mapping. Therefore it has received considerable attention recently. However, most of the existing methods are supervised and…
Generalizing to novel classes unseen during training is a key challenge of few-shot classification. Recent metric-based methods try to address this by local representations. However, they are unable to take full advantage of them due to (i)…
Feature extraction has gained increasing attention in the field of machine learning, as in order to detect patterns, extract information, or predict future observations from big data, the urge of informative features is crucial. The process…
Pansharpening is a widely used image enhancement technique for remote sensing. Its principle is to fuse the input high-resolution single-channel panchromatic (PAN) image and low-resolution multi-spectral image and to obtain a…
Land cover classification is a multi-class segmentation task to classify each pixel into a certain natural or man-made category of the earth surface, such as water, soil, natural vegetation, crops, and human infrastructure. Limited by…
As there are increasing needs of sharing data for machine learning, there is growing attention for the owners of the data to claim the ownership. Visible watermarking has been an effective way to claim the ownership of visual data, yet the…
We investigate the problem of representing an entire video using CNN features for human action recognition. Currently, limited by GPU memory, we have not been able to feed a whole video into CNN/RNNs for end-to-end learning. A common…
Live fish recognition is one of the most crucial elements of fisheries survey applications where vast amount of data are rapidly acquired. Different from general scenarios, challenges to underwater image recognition are posted by poor image…
Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective. In this paper, we…
Aiming at improving the performance of existing detection algorithms developed for different applications, we propose a region regression-based multi-stage class-agnostic detection pipeline, whereby the existing algorithms are employed for…
Salient object detection, which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite challenging,…
Background: Underwater images, in general, suffer from low contrast and high color distortions due to the non-uniform attenuation of the light as it propagates through the water. In addition, the degree of attenuation varies with the…
In recent years, deep learning based methods have achieved promising performance in standard object detection. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) Objects in…
Segmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits. Current approaches either downsample an ultra-high…
Feature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition. While learning-based methods have surpassed traditional handcrafted…
Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification. However, existing methods based on the…
Traditional change detection methods usually follow the image differencing, change feature extraction and classification framework, and their performance is limited by such simple image domain differencing and also the hand-crafted…