Timezone: »
Poster
The Distribution Family of Similarity Distances
Gertjan Burghouts · Arnold Smeulders · Jan-Mark Geusebroek
Assessing similarity between features is a key step in object recognition and scene categorization tasks. We argue that knowledge on the distribution of distances generated by similarity functions is crucial in deciding whether features are similar or not. Intuitively one would expect that similarities between features could arise from any distribution. In this paper, we will derive the contrary, and report the theoretical result that $L_p$-norms --a class of commonly applied distance metrics-- from one feature vector to other vectors are Weibull-distributed if the feature values are correlated and non-identically distributed. Besides these assumptions being realistic for images, we experimentally show them to hold for various popular feature extraction algorithms, for a diverse range of images. This fundamental insight opens new directions in the assessment of feature similarity, with projected improvements in object and scene recognition algorithms.
Author Information
Gertjan Burghouts (TNO - Intelligent Imaging)
Arnold Smeulders
Jan-Mark Geusebroek (University of Amsterdam)
More from the Same Authors
-
2021 : Equidistant Hyperspherical Prototypes Improve Uncertainty Quantification »
Gertjan Burghouts · Pascal Mettes -
2022 : Maximum Class Separation as Inductive Bias in One Matrix »
Tejaswi Kasarla · Gertjan Burghouts · Max van Spengler · Elise van der Pol · Rita Cucchiara · Pascal Mettes -
2022 : Unlocking Slot Attention by Changing Optimal Transport Costs »
Yan Zhang · David Zhang · Simon Lacoste-Julien · Gertjan Burghouts · Cees Snoek -
2022 : Self-Guided Diffusion Model »
TAO HU · David Zhang · Yuki Asano · Gertjan Burghouts · Cees Snoek -
2022 : Unlocking Slot Attention by Changing Optimal Transport Costs »
Yan Zhang · David Zhang · Simon Lacoste-Julien · Gertjan Burghouts · Cees Snoek -
2022 : Unlocking Slot Attention by Changing Optimal Transport Costs »
Yan Zhang · David Zhang · Simon Lacoste-Julien · Gertjan Burghouts · Cees Snoek -
2022 Spotlight: Lightning Talks 4B-2 »
Artem Moskalev · Weixia Zhang · Vudtiwat Ngampruetikorn · Anna Sepliarskaia · Dingquan Li · David Schwab · Ivan Sosnovik · Xiongkuo Min · Arnold Smeulders · Guangtao Zhai · Guodong Guo · Xiaokang Yang · Kede Ma -
2022 Spotlight: LieGG: Studying Learned Lie Group Generators »
Artem Moskalev · Anna Sepliarskaia · Ivan Sosnovik · Arnold Smeulders -
2022 Poster: LieGG: Studying Learned Lie Group Generators »
Artem Moskalev · Anna Sepliarskaia · Ivan Sosnovik · Arnold Smeulders -
2022 Poster: Maximum Class Separation as Inductive Bias in One Matrix »
Tejaswi Kasarla · Gertjan Burghouts · Max van Spengler · Elise van der Pol · Rita Cucchiara · Pascal Mettes -
2021 Poster: Independent Prototype Propagation for Zero-Shot Compositionality »
Frank Ruis · Gertjan Burghouts · Doina Bucur -
2009 Poster: A Biologically Plausible Model for Rapid Natural Scene Identification »
Sennay Ghebreab · H.Scholte Steven · Victor Lamme · Arnold Smeulders -
2007 Poster: Predicting Brain States from fMRI Data: Incremental Functional Principal Component Regression »
Sennay Ghebreab · Arnold Smeulders · Pieter Adriaans