Correction to: Contour analysis for interpretable leaf shape category discovery

Unfortunately, the original version of the article [1] contained an error in figure 7. The names of species Umus minor and Acer campestre were interchanged. The corrected figure 7 is given below:

Concepts as Causal Models

This chapter evaluates the case for treating concepts as causal models, the view that people conceive of a categories as consisting of not only features but also the causal relations that link those features. In particular, it reviews the role of causal models in category-based induction. Category-based induction consists of drawing inferences about either objects or categories; in the latter case one generalizes a feature to a category (and thus its members). How causal knowledge influences how categories are formed in the first place—causal-based category discovery—is also examined. Whereas the causal model approach provides a generally compelling account of a large variety of inductive inferences, certain key discrepancies between the theory and empirical findings are highlighted. The chapter concludes with a discussion of the new sorts of representations, tasks, and tests that should be applied to the causal model approach to concepts.

UNSUPERVISED DISCOVERY OF VISUAL FACE CATEGORIES

Human faces can be arranged into different face categories using information from common visual cues such as gender, ethnicity, and age. It has been demonstrated that using face categorization as a precursor step to face recognition improves recognition rates and leads to more graceful errors. Although face categorization using common visual cues yields meaningful face categories, developing accurate and robust gender, ethnicity, and age categorizers is a challenging issue. Moreover, it limits the overall number of possible face categories and, in practice, yields unbalanced face categories which can compromise recognition performance. This paper investigates ways to automatically discover a categorization of human faces from a collection of unlabeled face images without relying on predefined visual cues. Specifically, given a set of face images from a group of known individuals (i.e., gallery set), our goal is finding ways to robustly partition the gallery set (i.e., face categories). The objective is being able to assign novel images of the same individuals (i.e., query set) to the correct face category with high accuracy and robustness. To address the issue of face category discovery, we represent faces using local features and apply unsupervised learning (i.e., clustering). To categorize faces in novel images, we employ nearest-neighbor algorithms or learn the separating boundaries between face categories using supervised learning (i.e., classification). To improve face categorization robustness, we allow face categories to share local features as well as to overlap. We demonstrate the performance of the proposed approach through extensive experiments and comparisons using the FERET database.