Track topics on Twitter Track topics that are important to you
Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently some researchers attempted to use object-level labels (e.g. bounding boxes) or image-level labels (e.g. image categories). In this paper, we propose a novel recursive coarse-to-fine semantic segmentation framework based on only image-level category labels. For each image, an initial coarse mask is first generated by a convolutional neural network-based unsupervised foreground segmentation model and then is enhanced by a graph model. The enhanced coarse mask is fed to a fully convolutional neural network to be recursively refined. Unlike existing image-level label-based semantic segmentation methods which require to label all categories for images contain multiple types of objects, our framework only needs one label for each image and can handle images contains multi-category objects. With only trained on ImageNet, our framework achieves comparable performance on PASCAL VOC dataset as other image-level label-based state-of-the-arts of semantic segmentation. Furthermore, our framework can be easily extended to foreground object segmentation task and achieves comparable performance with the state-of-the-art supervised methods on the Internet Object dataset.
This article was published in the following journal.
Name: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
We propose Neural Image Compression (NIC), a two-step method to build convolutional neural networks for gigapixel image analysis solely using weak image-level labels. First, gigapixel images are compr...
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised se...
Semantic image segmentation is an important yet unsolved problem. One of the major challenges is the large variability of the object scales. To tackle this scale problem, we propose a Scale-Adaptive N...
Attributes are semantically meaningful characteristics whose applicability widely crosses category boundaries. They are particularly important in describing and recognizing concepts for which no expli...
Effectively recognizing different sceneries with complex backgrounds and varied lighting conditions plays an important role in modern AI systems. Competitive performance has recently been achieved by ...
The primary objective of the study is to show that ventilation heterogeneity identified by hyperpolarized helium-3 lung MRI is prevalent children with poorly controlled asthma despite guid...
This is a prospective randomized clinical trial examining how IRIS (Intelligent Real-time Image Segmentation) affects biopsy patterns in VLE (Volumetric laser endomicroscopy).
Most studies on menu labels have been conducted in mostly non-Hispanic white individuals, and how menu labels affect calories and macronutrients ordered in Hispanics is not clearly underst...
The aim of this study is to compare different sugary drink labels to see which most influence knowledge, beliefs, purchase intentions and choices. Parents of children ages 6-11 will shop i...
The primary objective of this study is to determine to what degree sugary drink warning labels increase consumers' knowledge about the potential health harms of sugary drinks and reduce su...
A framework for development and promotion of common data formats and exchange protocols linked in a way that can be read directly by computers. Semantic Web is a platform for sharing and reusing data across application, enterprise, and community boundaries, by linking concepts rather than just documents.
Improvement of the quality of a picture by various techniques, including computer processing, digital filtering, echocardiographic techniques, light and ultrastructural MICROSCOPY, fluorescence spectrometry and microscopy, scintigraphy, and in vitro image processing at the molecular level.
RNA, usually prepared by transcription from cloned DNA, which complements a specific mRNA or DNA and is generally used for studies of virus genes, distribution of specific RNA in tissues and cells, integration of viral DNA into genomes, transcription, etc. Whereas DNA PROBES are preferred for use at a more macroscopic level for detection of the presence of DNA/RNA from specific species or subspecies, RNA probes are preferred for genetic studies. Conventional labels for the RNA probe include radioisotope labels 32P and 125I and the chemical label biotin. RNA probes may be further divided by category into plus-sense RNA probes, minus-sense RNA probes, and antisense RNA probes.
A method of delineating blood vessels by subtracting a tissue background image from an image of tissue plus intravascular contrast material that attenuates the X-ray photons. The background image is determined from a digitized image taken a few moments before injection of the contrast material. The resulting angiogram is a high-contrast image of the vessel. This subtraction technique allows extraction of a high-intensity signal from the superimposed background information. The image is thus the result of the differential absorption of X-rays by different tissues.
Using fine needles (finer than 22-gauge) to remove tissue or fluid specimens from the living body for examination in the pathology laboratory and for disease diagnosis.
Standard antiretroviral therapy (ART) consists of the combination of at least three antiretroviral (ARV) drugs to maximally suppress the HIV virus and stop the progression of HIV disease. Huge reductions have been seen in rates of death and suffering whe...