The Experts below are selected from a list of 45 Experts worldwide ranked by ideXlab platform
Lei Zhang - One of the best experts on this subject based on the ideXlab platform.
-
ECCV (7) - Shrinkage Expansion Adaptive Metric Learning
Computer Vision – ECCV 2014, 2014Co-Authors: Qilong Wang, Wangmeng Zuo, Lei ZhangAbstract:Conventional Pairwise constrained metric learning methods usually restrict the distance between samples of a similar Pair to be lower than a fixed upper bound, and the distance between samples of a Dissimilar Pair higher than a fixed lower bound. Such fixed bound based constraints, however, may not work well when the intra- and inter-class variations are complex. In this paper, we propose a shrinkage expansion adaptive metric learning (SEAML) method by defining a novel shrinkage-expansion rule for adaptive Pairwise constraints. SEAML is very effective in learning metrics from data with complex distributions. Meanwhile, it also suggests a new rule to assess the similarity between a Pair of samples based on whether their distance is shrunk or expanded after metric learning. Our extensive experimental results demonstrated that SEAML achieves better performance than state-of-the-art metric learning methods. In addition, the proposed shrinkage-expansion adaptive Pairwise constraints can be readily applied to many other Pairwise constrained metric learning algorithms, and boost significantly their performance in applications such as face verification on LFW and PubFig databases.
Bin Fant - One of the best experts on this subject based on the ideXlab platform.
-
ICPR - Cayley- Klein Metric Learning with Shrinkage-Expansion Constraints
2018 24th International Conference on Pattern Recognition (ICPR), 2018Co-Authors: Bin FantAbstract:Cayley-Klein metric is a specific kind of non-Euclidean metric in projective space. Recently, it has been introduced into metric learning with encouraging performance when dealing with computer vision tasks. However, the original Cayley-Klein metric learning methods with conventional Pairwise and triplet-wise constraints, which are fixed bound based constraints, may not perform well when the intra-and inter-class variations of data distribution become complex. Pairwise constraints restrict the distance between samples of a similar Pair to be lower than a fixed upper bound, and the distance between samples of a Dissimilar Pair higher than a fixed lower bound. Triplet-wise constraints restrict the distance between samples of a similar Pair to be smaller than that between a Pair of samples from different classes. In this paper, we propose a novel Cayley-Klein metric learning method (CKseML) with adaptive shrinkage-expansion Pairwise constraints. CKseML is very effective in learning metric from data with complex distributions. Our experimental results demonstrate that CKseML achieves better performance than the original Cayley-Klein metric learning methods.
Qilong Wang - One of the best experts on this subject based on the ideXlab platform.
-
ECCV (7) - Shrinkage Expansion Adaptive Metric Learning
Computer Vision – ECCV 2014, 2014Co-Authors: Qilong Wang, Wangmeng Zuo, Lei ZhangAbstract:Conventional Pairwise constrained metric learning methods usually restrict the distance between samples of a similar Pair to be lower than a fixed upper bound, and the distance between samples of a Dissimilar Pair higher than a fixed lower bound. Such fixed bound based constraints, however, may not work well when the intra- and inter-class variations are complex. In this paper, we propose a shrinkage expansion adaptive metric learning (SEAML) method by defining a novel shrinkage-expansion rule for adaptive Pairwise constraints. SEAML is very effective in learning metrics from data with complex distributions. Meanwhile, it also suggests a new rule to assess the similarity between a Pair of samples based on whether their distance is shrunk or expanded after metric learning. Our extensive experimental results demonstrated that SEAML achieves better performance than state-of-the-art metric learning methods. In addition, the proposed shrinkage-expansion adaptive Pairwise constraints can be readily applied to many other Pairwise constrained metric learning algorithms, and boost significantly their performance in applications such as face verification on LFW and PubFig databases.
Rumi Tokunaga - One of the best experts on this subject based on the ideXlab platform.
-
colour constancy as measured by least Dissimilar matching
Seeing and Perceiving, 2011Co-Authors: Alexander D Logvinenko, Rumi TokunagaAbstract:Although asymmetric colour matching has been widely used in experiments on colour constancy, an exact colour match between objects lit by different chromatic lights is impossible to achieve. We used a modification of this technique, instructing our observers to establish the least Dissimilar Pair of differently illuminated coloured papers. The stimulus display consisted of two identical sets of 22 Munsell papers illuminated independently by neutral, yellow, blue, green and red lights. The lights produced approximately the same illuminance. Four trichromatic observers participated in the experiment. The proportion of exact matches was evaluated. When both sets of papers were lit by the same light, the exact match rate was 0.92, 0.93, 0.84, 0.78 and 0.76 for the neutral, yellow, blue, green and red lights, respectively. When one illumination was neutral and the other chromatic, the exact match rate was 0.80, 0.40, 0.56 and 0.32 for the yellow, blue, green and red lights, respectively. When both lights were chromatic, the exact match rate was found to be even poorer (0.30 on average). Yet, least Dissimilar matching was found to be rather systematic. Particularly, a statistical test showed it was symmetric and transitive. The exact match rate was found to be different for different papers, varying from 0.99 (black paper) to 0.12 (purple paper). Such a variation can hardly be expected if observers' judgements were based on an illuminant estimate. We argue that colour constancy cannot be achieved for all the reflecting objects because of mismatching of metamers. We conjecture that the visual system might have evolved to have colour constant perception for some ecologically valid objects at a cost of colour inconstancy for other types of objects.
Ruth Kennedy - One of the best experts on this subject based on the ideXlab platform.
-
Similarity comparisons with remembered and perceived magnitudes: memory psychophysics and fundamental measurement.
Memory & cognition, 1998Co-Authors: William M. Petrusic, Joseph V. Baranski, Ruth KennedyAbstract:At the outset, subjects learned to associate a label with each element in a set of perceptual magnitudes (visual extents), using traditional Paired-associate learning methods. Subsequently, on some trials, subjects indicated which Pair of two Pairs of labels corresponded to the more similar perceptual referents, and, on other trials, they selected the more Dissimilar Pair. It is shown that these similarity comparisons satisfy the axioms (transitivity and intradimensional subtractivity) necessary to conclude that they are based on computation of the difference of the differences of analogue-based interval scale representations.The findings also permitted refutation of the idea that memory for elementary percepts arises from their reperception. Notably, the memory exponent was 0.697, but the perception exponent was 0.546, and the reperception idea requires that the memory exponent be the square of the perception exponent (0.5462=0.298). Symbolic distance effects and enhanced response time-based semantic congruity effects, typically found with binary comparisons, extend the range of commonalties found between perceptual and memory psychophysics.