Image semantic segmentation is one of the most important tasks in the field of computer
vision, and it has made great progress in many applications. Many fully supervised deep …

The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Image classification systems recently made a giant leap with the advancement of deep
neural networks. However, these systems require an excessive amount of labeled data to be …

In this work, we investigate the problem of learning knowledge from the massive community-
contributed images with rich weakly-supervised context information, which can benefit …

Convolutional neural networks (CNNs) have gained tremendous success in solving complex
inverse problems. The aim of this work is to develop a novel CNN framework to reconstruct …

Discovering disease-gene association is a fundamental and critical biomedical task, which
assists biologists and physicians to discover pathogenic mechanism of syndromes. With …

The success of current deep saliency detection methods heavily depends on the availability
of large-scale supervision in the form of per-pixel labeling. Such supervision, while labor …

A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide
spectrum of high dynamic range (HDR) content is quintessential for visualization on varied …

State of the art methods for semantic image segmentation are trained in a supervised
fashion using a large corpus of fully labeled training images. However, gathering such a …

There is an emerging trend to leverage noisy image datasets in many visual recognition
tasks. However, the label noise among datasets severely degenerates the performance of …