In this work we address the task of semantic image segmentation with Deep Learning and
make three main contributions that are experimentally shown to have substantial practical …

Deep learning has revolutionalized image-level tasks such as classification, but patch-level
tasks, such as correspondence, still rely on hand-crafted features, eg SIFT. In this paper we …

Wireless sensor networks are composed of large numbers of tiny networked devices that
communicate untethered. For large scale networks, it is important to be able to download …

We introduce an approach to integrate segmentation information within a convolutional
neural network (CNN). This counter-acts the tendency of CNNs to smooth information across …

The dominant approach for learning local patch descriptors relies on small image regions
whose scale must be properly estimated a priori by a keypoint detector. In other words, if two …

We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic
correspondence. To robustly match points among different instances within the same object …

Finding image correspondences remains a challenging problem in the presence of intra-
class variations and large changes in scene layout. Semantic flow methods are designed to …

Finding image correspondences remains a challenging problem in the presence of intra-
class variations and large changes in scene layout. Semantic flow methods are designed to …

Image matching is a fundamental problem in Computer Vision. In the context of feature-
based matching, SIFT and its variants have long excelled in a wide array of applications …

Recent investigations on human vision discover that the retinal image is a landscape or a
geometric surface, consisting of features such as ridges and summits. However, most of …