Sort by: Year Popularity Relevance

Individual common dolphin identification via metric embedding learning

, , ,  - 2019

Photo-identification (photo-id) of dolphin individuals is a commonly used technique in ecological sciences to monitor state and health of individuals, as well as to study the social structure and distribution of a population. Traditional photo-id involves a laborious manual process of matching each dolphin fin photograph captured in the field to ...


Disease Knowledge Transfer across Neurodegenerative Diseases

, , , , , , , , ,  - 2019

We introduce Disease Knowledge Transfer (DKT), a novel technique for transferring biomarker information between related neurodegenerative diseases. DKT infers robust multimodal biomarker trajectories in rare neurodegenerative diseases even when only limited, unimodal data is available, by transferring information from larger multimodal datasets f...


PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

, , ,  - 2019

PointNet has revolutionized how we think about representing point clouds. For classification and segmentation tasks, the approach and its subsequent extensions are state-of-the-art. To date, the successful application of PointNet to point cloud registration has remained elusive. In this paper we argue that PointNet itself can be thought of as a l...


The Benefits of Over-parameterization at Initialization in Deep ReLU Networks

,  - 2019

It has been noted in existing literature that over-parameterization in ReLU networks generally leads to better performance. While there could be several reasons for this, we investigate desirable network properties at initialization which may be enjoyed by ReLU networks. Without making any assumption, we derive a lower bound on the layer width of...


Understanding the Impact of Label Granularity on CNN-based Image Classification

, , ,  - 2019

In recent years, supervised learning using Convolutional Neural Networks (CNNs) has achieved great success in image classification tasks, and large scale labeled datasets have contributed significantly to this achievement. However, the definition of a label is often application dependent. For example, an image of a cat can be labeled as "cat" or ...


Bonsai - Diverse and Shallow Trees for Extreme Multi-label Classification

, ,  - 2019

Extreme multi-label classification refers to supervised multi-label learning involving hundreds of thousand or even millions of labels. In this paper, we develop a shallow tree-based algorithm, called Bonsai, which promotes diversity of the label space and easily scales to millions of labels. Bonsai relaxes the two main constraints of the recentl...


Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation

, , ,  - 2019

Supervised depth estimation has achieved high accuracy due to the advanced deep network architectures. Since the groundtruth depth labels are hard to obtain, recent methods try to learn depth estimation networks in an unsupervised way by exploring unsupervised cues, which are effective but less reliable than true labels. An emerging way to resolv...


Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning

, , , ,  - 2019

A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this paper, we provide a general weighting framework for understanding recent pair-based loss functions. Our contributions are three-fold: (1) we establish a General Pair Weighting (GPW) ...


Preferences Implicit in the State of the World

, , , ,  - 2019

Reinforcement learning (RL) agents optimize only the features specified in a reward function and are indifferent to anything left out inadvertently. This means that we must not only specify what to do, but also the much larger space of what not to do. It is easy to forget these preferences, since these preferences are already satisfied in our env...


Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

, ,  - 2019

Many computer vision challenges require continuous outputs, but tend to be solved by discrete classification. The reason is classification's natural containment within a probability $n$-simplex, as defined by the popular softmax activation function. Regular regression lacks such a closed geometry, leading to unstable training and convergence to s...