Metric visual information about distance entails informational units
نویسندگان
چکیده
منابع مشابه
Parametric Distance Metric Learning with Label Information
Distance-based methods in pattern recognition and machine learning have to rely on a similarity or dissimilarity measure between patterns in the input space. For many applications, Euclidean distance in the input space is not a good choice and hence more complicated distance metrics have to be used. In this paper, we propose a parametric method for metric learning based on class label informati...
متن کاملCultural Evolution Entails (Creativity Entails (Concept Combination Entails Quantum Structure))
The theory of natural selection cannot describe how early life evolved, in part because acquired characteristics are passed on through horizontal exchange. It has been proposed that culture, like life, began with the emergence of autopoietic form, thus its evolution too cannot be described by natural selection. The evolution of autopoietic form can be described using a framework referred to as ...
متن کاملSemi-supervised Distance Metric Learning for Visual Object Classification
This paper describes a semi-supervised distance metric learning algorithm which uses pairwise equivalence (similarity and dissimilarity) constraints to discover the desired groups within high-dimensional data. As opposed to the traditional full rank distance metric learning algorithms, the proposed method can learn nonsquare projection matrices that yield low rank distance metrics. This brings ...
متن کاملVisual Homing with Learned Goal Distance Information
Zeil et. al. (2003) demonstrated that the image difference between a panoramic image taken at a particular goal position and panoramic images captured nearby is highly correlated with the spatial distance between the locations at which the images were captured. They defined image difference as the rootmeansquare intensity difference over all image pixels (RMS). We recently showed (Szenher, 20...
متن کاملDistance Metric Learning with Application to Clustering with Side-Information
Many algorithms rely critically on being given a good metric over their inputs. For instance, data can often be clustered in many “plausible” ways, and if a clustering algorithm such as K-means initially fails to find one that is meaningful to a user, the only recourse may be for the user to manually tweak the metric until sufficiently good clusters are found. For these and other applications r...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Vision
سال: 2011
ISSN: 1534-7362
DOI: 10.1167/11.11.972