Related papers: CPMetric: Deep Siamese Networks for Learning Dista…

Most existing recommender systems represent a user's preference with a feature vector, which is assumed to be fixed when predicting this user's preferences for different items. However, the same vector cannot accurately capture a user's…

Transportation distances have been used for more than a decade now in machine learning to compare histograms of features. They have one parameter: the ground metric, which can be any metric between the features themselves. As is the case…

Most Machine Learning (ML) methods, from clustering to classification, rely on a distance function to describe relationships between datapoints. For complex datasets it is hard to avoid making some arbitrary choices when defining a distance…

It is generally well understood that predictive classification and compression are intrinsically related concepts in information theory. Indeed, many deep learning methods are explained as learning a kind of compression, and that better…

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

Tracking by detection is a common approach to solving the Multiple Object Tracking problem. In this paper we show how learning a deep similarity metric can improve three key aspects of pedestrian tracking on a multiple object tracking…

We present a novel non-iterative learnable method for partial-to-partial 3D shape registration. The partial alignment task is extremely complex, as it jointly tries to match between points and identify which points do not appear in the…

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens.…

Learning generic representations with deep networks requires massive training samples and significant computer resources. To learn a new specific task, an important issue is to transfer the generic teacher's representation to a student…

In this paper, we propose a new Deep Neural Network (DNN) testing algorithm called the Constrained Gradient Descent (CGD) method, and an implementation we call CGDTest aimed at exposing security and robustness issues such as adversarial…

Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be…

In collaborative filtering, distance metric learning has been applied to matrix factorization techniques with promising results. However, matrix factorization lacks the ability of capturing collaborative information, which has been remarked…

We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss functions. In…

Learning an effective representation of 3D point clouds requires a good metric to measure the discrepancy between two 3D point sets, which is non-trivial due to their irregularity. Most of the previous works resort to using the Chamfer…

We propose a class of semimetrics for preference relations any one of which is an alternative to the classical Kemeny-Snell-Bogart metric. (We take a fairly general viewpoint about what constitutes a preference relation, allowing for any…

Depth prediction is one of the fundamental problems in computer vision. In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for various depth estimation tasks.…

The Algonauts challenge is about predicting the object representations in the form of Representational Dissimilarity Matrices (RDMS) derived from visual brain regions. We used a customized deep learning model using the concept of Siamese…

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in…

The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in…