The origins of the shape bias: Evidence from the Tsimane'

In the US, children often generalize the meaning of new words by assuming that objects with the same shape have the same name. We propose that this shape bias is influenced by children’s exposure to objects of different categories (artifacts and natural kinds), and language to talk about them. We present a cross-cultural study between English speakers in the US and Tsimane’ speakers in the Bolivian Amazon. We found that US children and adults were more likely to generalize novel labels by shape rather than by material or color, relative to Tsimane’ participants. Critically, Tsimane’ children and adults systematically avoided generalizing labels to objects that shared no common features with the novel referent. Our results provide initial evidence that the relative exposure to objects of different kinds and language to talk about them can lead to cross-cultural differences on object name learning.

DuFeNet: Improve the Accuracy and Increase Shape Bias of Neural Network Models

In image classification field, existing work tends to modify the network structure to obtain higher accuracy or faster speed. However, some studies have found that the neural network usually has texture bias effect, which means that the neural network is more sensitive to the texture information than the shape information. Based on such phenomenon, we propose a new way to improve network performance by making full use of gradient information. The dual features network (DuFeNet) is proposed in this paper. In DuFeNet, one sub-network is used to learn the information of gradient features, and the other is a traditional neural network with texture bias. The structure of DuFeNet is easy to implement in the original neural network structure. The experimental results clearly show that DuFeNet can achieve better accuracy in image classification and detection. It can increase the shape bias of the network adapted to human visual perception. Besides, DuFeNet can be used without modifying the structure of the original network at lower additional parameters cost.

Vocabulary Development and the Shape Bias in Children With Hearing Loss

Purpose Although children with hearing loss (HL) can benefit from cochlear implants (CIs) and hearing aids (HAs), they often show language delays. Moreover, little is known about the mechanisms by which children with HL learn words. One mechanism by which typically hearing (TH) children learn words is by acquiring word learning biases such as the “shape bias,” that is, generalizing the names of novel solid objects by similarity in shape. In TH children, the shape bias emerges out of regularities in the early vocabulary and, once acquired, has consequences for subsequent vocabulary development. Method Here, we ask whether children with HL exhibit similar word learning biases as TH children. In the current study, nineteen 2- to 3.5-year-old children with HL generalized the names of novel objects by similarity in shape or material. We compared their performance to that of 20 TH children matched on age and 20 TH children matched on vocabulary size. Results Children with HL were significantly less likely than age-matched TH children and vocabulary-matched TH children to generalize novel names to objects of the same shape. However, there was also an interaction such that vocabulary has a stronger effect on novel noun generalization for those with HL than for those who are TH. Exploratory analyses of children with HL reveal similar novel noun generalization and vocabulary sizes in children who use CIs and those who use HAs, regardless of hearing age or degree of HL. Conclusion Together, the results suggest that, although vocabulary knowledge drives development of the shape bias in general for all children, it may be especially important for children with HL, who are at risk for language delays.

Beyond the Shape of Things: Infants Can Be Taught to Generalize Nouns by Objects’ Functions

Two-year-olds typically extend labels of novel objects by the objects’ shape ( shape bias), whereas adults do so by the objects’ function. Is this because shape is conceptually easier to comprehend than function? To test whether the conceptual complexity of function prevents infants from developing a function bias, we trained twelve 17-month-olds (function-training group) to focus on objects’ functions when labeling the objects over a period of 7 weeks. Our training was similar to previously used methods in which 17-month-olds were successfully taught to focus on the shape of objects, resulting in a precocious shape bias. We exposed another 12 infants (control group) to the same objects over 7 weeks but without labeling the items or demonstrating their functions. Only the infants in the function-training group developed a function bias. Thus, the conceptual complexity of function was not a barrier for developing a function bias, which suggests that the shape bias emerges naturally because shape is perceptually more accessible than function.

Increasing Shape Bias to Improve the Precision of Center Pivot Irrigation System Detection

Irrigation is indispensable in agriculture. Center pivot irrigation systems are popular means of irrigation since they are water-efficient and labor-saving. Monitoring center pivot irrigation systems provides important information for the understanding of agricultural production, water resources consumption and environmental change. Deep learning has become an effective approach for object detection and semantic segmentation. Recent studies have shown that convolutional neural networks (CNNs) are prone to be texture-biased rather than shape-biased, and increasing shape bias can improve the robustness and performance of CNNs. In this study, a simple yet effective method was proposed to increase shape bias in object detection networks to improve the precision of center pivot irrigation system detection. We extracted edge images of training samples and integrated them into the training data to increase shape bias in the networks. With the proposed shape increasing training scheme, we evaluated and compared PVANET and YOLOv4. Experiments with the images in Mato Grosso have shown that both PVANET and YOLOv4 achieved improved performance, which demonstrated the validity of the proposed method.

Iterated shape-bias graph cut with application to ellipse segmentation

We present a novel graph cut method for iterated segmentation of objects with specific shape bias (SBGC). In contrast with conventional graph cut models which emphasize the regional appearance only, the proposed SBGC takes the shape preference of the interested object into account to drive the segmentation. Therefore, the SBGC can ensure a more accurate convergence to the interested object even in complicated conditions where the appearance cues are inadequate for object/background discrimination. In particular, we firstly evaluate the segmentation by simultaneously considering its global shape and local edge consistencies with the object shape priors. Then these two cues are formulated into a graph cut framework to seek the optimal segmentation that maximizing both of the global and local measurements. By iteratively implementing the optimization, the proposed SBGC can achieve joint estimation of the optimal segmentation and the most likely object shape encoded by the shape priors, and eventually converge to the candidate result with maximum consistency between these two estimations. Finally, we take the ellipse shape objects with various segmentation challenges as examples for evaluation. Competitive results compared with state-of-the-art methods validate the effectiveness of the technique.

What categorical induction variability reveals about typical and atypical development

Categorical induction abilities are robust in typically developing (TD) preschoolers, while children with Autism Spectrum Disorders (ASD) frequently perform inconsistently on tasks asking for the transference of traits from a known category member to a new example based on shared category membership. Here, TD five-year-olds and six-year-olds with ASD participated in a categorical induction task; the TD children performed significantly better and more consistently than the children with ASD. Concurrent verbal and nonverbal tests were not significant correlates; however, the TD children's shape bias performance at two years of age was significantly positively predictive of categorical induction performance at age five. The shape bias, the tendency to extend a novel label to other objects of the same shape during word learning, appears linked with categorical induction ability in TD children, suggesting a common underlying skill and consistent developmental trajectory. Word learning and categorical induction appear uncoupled in children with ASD.