PerceptNet: Learning Perceptual Similarity of Haptic Textures in Presence of Unorderable Triplets
This addresses the need for a reliable perceptual similarity metric in haptics to avoid ambiguity in haptic vocabulary design, representing an incremental improvement over prior non-parametric methods.
The paper tackles the problem of accurately estimating perceptual dissimilarity of haptic signals for designing haptic icons, presenting a deep neural network method that learns a perceptual metric from human study data, with results showing it is significantly more effective than alternatives.
In order to design haptic icons or build a haptic vocabulary, we require a set of easily distinguishable haptic signals to avoid perceptual ambiguity, which in turn requires a way to accurately estimate the perceptual (dis)similarity of such signals. In this work, we present a novel method to learn such a perceptual metric based on data from human studies. Our method is based on a deep neural network that projects signals to an embedding space where the natural Euclidean distance accurately models the degree of dissimilarity between two signals. The network is trained only on non-numerical comparisons of triplets of signals, using a novel triplet loss that considers both types of triplets that are easy to order (inequality constraints), as well as those that are unorderable/ambiguous (equality constraints). Unlike prior MDS-based non-parametric approaches, our method can be trained on a partial set of comparisons and can embed new haptic signals without retraining the model from scratch. Extensive experimental evaluations show that our method is significantly more effective at modeling perceptual dissimilarity than alternatives.