Category-specific Features Research Articles

Perceptual Expertise and Attention: An Exploration using Deep Neural Networks.

Perceptual expertise and attention are two important factors that enable superior object recognition and task performance. While expertise enhances knowledge and provides a holistic understanding of the environment, attention allows us to selectively focus on task-related information and suppress distraction. It has been suggested that attention operates differently in experts and in novices, but much remains unknown. This study investigates the relationship between perceptual expertise and attention using convolutional neural networks (CNNs), which are shown to be good models of primate visual pathways. Two CNN models were trained to become experts in either face or scene recognition, and the effect of attention on performance was evaluated in tasks involving complex stimuli, such as superimposed images containing superimposed faces and scenes. The goal was to explore how feature-based attention (FBA) influences recognition within and outside the domain of expertise of the models. We found that each model performed better in its area of expertise-and that FBA further enhanced task performance, but only within the domain of expertise, increasing performance by up to 35% in scene recognition, and 15% in face recognition. However, attention had reduced or negative effects when applied outside the models' expertise domain. Neural unit-level analysis revealed that expertise led to stronger tuning towards category-specific features and sharper tuning curves, as reflected in greater representational dissimilarity between targets and distractors, which, in line with the biased competition model of attention, leads to enhanced performance by reducing competition. These findings highlight the critical role of neural tuning at single as well as network level neural in distinguishing the effects of attention in experts and in novices and demonstrate that CNNs can be used fruitfully as computational models for addressing neuroscience questions not practical with the empirical methods.

Motor Imagery Recognition Based on GMM-JCSFE Model.

Features from EEG microstate models, such as time-domain statistical features and state transition probabilities, are typically manually selected based on experience. However, traditional microstate models assume abrupt transitions between states, and the classification features can vary among individuals due to personal differences. To date, both empirical and theoretical classification results of EEG microstate features have not been entirely satisfactory. Here, we introduce an enhanced feature extraction method that combines Joint label-Common and label-Specific Feature Exploration (JCSFE) with Gaussian Mixture Models (GMM) to explore microstate features. First, GMMs are employed to represent the smooth transitions of EEG spatiotemporal features within microstate models. Second, category-common and category-specific features are identified by applying regularization constraints to linear classifiers. Third, a graph regularizer is used to extract subject-invariant microstate features. Experimental results on publicly available datasets demonstrate that the proposed model effectively encodes microstate features and improves the accuracy of motor imagery recognition across subjects. The primary code is accessible for download from the website: https://github.com/liaoliao3450/GMM-JCSFE.

TransDose: Transformer-based radiotherapy dose prediction from CT images guided by super-pixel-level GCN classification.

Radiotherapy is a mainstay treatment for cancer in clinic. An excellent radiotherapy treatment plan is always based on a high-quality dose distribution map which is produced by repeated manual trial-and-errors of experienced experts. To accelerate the radiotherapy planning process, many automatic dose distribution prediction methods have been proposed recently and achieved considerable fruits. Nevertheless, these methods require certain auxiliary inputs besides CT images, such as segmentation masks of the tumor and organs at risk (OARs), which limits their prediction efficiency and application potential. To address this issue, we design a novel approach named as TransDose for dose distribution prediction that treats CT images as the unique input in this paper. Specifically, instead of inputting the segmentation masks to provide the prior anatomical information, we utilize a super-pixel-based graph convolutional network (GCN) to extract category-specific features, thereby compensating the network for the necessary anatomical knowledge. Besides, considering the strong continuous dependency between adjacent CT slices as well as adjacent dose maps, we embed the Transformer into the backbone, and make use of its superior ability of long-range sequence modeling to endow input features with inter-slice continuity message. To our knowledge, this is the first network that specially designed for the task of dose prediction from only CT images without ignoring necessary anatomical structure. Finally, we evaluate our model on two real datasets, and extensive experiments demonstrate the generalizability and advantages of our method.

Semantic Decomposition Network With Contrastive and Structural Constraints for Dental Plaque Segmentation.

Segmenting dental plaque from images of medical reagent staining provides valuable information for diagnosis and the determination of follow-up treatment plan. However, accurate dental plaque segmentation is a challenging task that requires identifying teeth and dental plaque subjected to semantic-blur regions (i.e., confused boundaries in border regions between teeth and dental plaque) and complex variations of instance shapes, which are not fully addressed by existing methods. Therefore, we propose a semantic decomposition network (SDNet) that introduces two single-task branches to separately address the segmentation of teeth and dental plaque and designs additional constraints to learn category-specific features for each branch, thus facilitating the semantic decomposition and improving the performance of dental plaque segmentation. Specifically, SDNet learns two separate segmentation branches for teeth and dental plaque in a divide-and-conquer manner to decouple the entangled relation between them. Each branch that specifies a category tends to yield accurate segmentation. To help these two branches better focus on category-specific features, two constraint modules are further proposed: 1) contrastive constraint module (CCM) to learn discriminative feature representations by maximizing the distance between different category representations, so as to reduce the negative impact of semantic-blur regions on feature extraction; 2) structural constraint module (SCM) to provide complete structural information for dental plaque of various shapes by the supervision of an boundary-aware geometric constraint. Besides, we construct a large-scale open-source Stained Dental Plaque Segmentation dataset (SDPSeg), which provides high-quality annotations for teeth and dental plaque. Experimental results on SDPSeg datasets show SDNet achieves state-of-the-art performance.

Category-Aware Aircraft Landmark Detection

Aircraft landmark detection (ALD) aims at detecting the keypoints of aircraft, which can serve as an important role for subsequent applications such as fine-grained aircraft recognition. In ALD, the physical size discrepancy between different kinds of aircraft may lead to inconsistent landmark structure, which significantly harms landmark detection results. In this letter, we take advantage of the category prior to alleviate the size discrepancy in ALD. The proposed category-aware landmark detection network (CALDN) possesses two streams: a classification stream for size categorization and a localization stream for landmark detection. Instance-level size category information captured by classification stream serves as the guidance in the localization stream for robust landmark detection. Moreover, a category attention module (CAM) is proposed for better-utilizing category information to guide ALD. Benefitting from the adaptive attention mechanism, CAM can automatically highlight category-specific features for ulteriorly reducing the influence of size discrepancy. Furthermore, to advance ALD research, we contribute the first perspective-variant aircraft landmark dataset. Solid experiments demonstrate the superiority of our method.

Learning Structural Representations via Dynamic Object Landmarks Discovery for Sketch Recognition and Retrieval.

State-of-the-art methods on sketch classification and retrieval are based on deep convolutional neural network to learn representations. Although deep neural networks have the ability to model images with hierarchical representations by convolution kernels, they can not automatically extract the structural representations of object categories in a human-perceptible way. Furthermore, sketch images usually have large scale visual variations caused by the styles of drawing or viewpoints, which make it difficult to develop generalized representations using the fixed computational mode of convolutional kernel. In this paper, our aim is to address the problem of fixed computational mode in feature extraction process without extra supervision. We propose a novel architecture to dynamically discover the object landmarks and learn the discriminative structural representations. Our model is composed of two components: a representative landmark discovering module that localizes the key points on the object, and a category-aware representation learning module that develops the category-specific features. Specifically, we develop a structure-aware offset layer to dynamically localize the representative landmarks, which is optimized based on the category labels without extra supervision. After that, a diversity branch is introduced to extract the global discriminative features for each category. Finally, we employ a multi-task loss function to develop an end-to-end trainable architecture. At testing time, we fuse all the predictions with different number of landmarks to achieve the final results. Through extensive experiments, we compare our model with several state-of-the-art methods on two challenging datasets TU-Berlin and Sketchy for sketch classification and retrieval, and the experimental results demonstrate the effectiveness of our proposed model.

Branch-Activated Multi-Domain Convolutional Neural Network for Visual Tracking

Convolutional neural networks (CNNs) have been applied in state-of-the-art visual tracking tasks to represent the target. However, most existing algorithms treat visual tracking as an object-specific task. Therefore, the model needs to be retrained for different test video sequences. We propose a branch-activated multi-domain convolutional neural network (BAMDCNN). In contrast to most existing trackers based on CNNs which require frequent online training, BAMDCNN only needs offline training and online fine-tuning. Specifically, BAMDCNN exploits category-specific features that are more robust against variations. To allow for learning category-specific information, we introduce a group algorithm and a branch activation method. Experimental results on challenging benchmark show that the proposed algorithm outperforms other state-of-the-art methods. What’s more, compared with CNN based trackers, BAMDCNN increases tracking speed.

Deformation-driven shape correspondence via shape recognition

Many approaches to shape comparison and recognition start by establishing a shape correspondence. We "turn the table" and show that quality shape correspondences can be obtained by performing many shape recognition tasks. What is more, the method we develop computes a fine-grained, topology-varying part correspondence between two 3D shapes where the core evaluation mechanism only recognizes shapes globally. This is made possible by casting the part correspondence problem in a deformation-driven framework and relying on a data-driven "deformation energy" which rates visual similarity between deformed shapes and models from a shape repository. Our basic premise is that if a correspondence between two chairs (or airplanes, bicycles, etc.) is correct, then a reasonable deformation between the two chairs anchored on the correspondence ought to produce plausible , "chair-like" in-between shapes. Given two 3D shapes belonging to the same category, we perform a top-down, hierarchical search for part correspondences. For a candidate correspondence at each level of the search hierarchy, we deform one input shape into the other, while respecting the correspondence, and rate the correspondence based on how well the resulting deformed shapes resemble other shapes from ShapeNet belonging to the same category as the inputs. The resemblance, i.e., plausibility, is measured by comparing multi-view depth images over category-specific features learned for the various shape categories. We demonstrate clear improvements over state-of-the-art approaches through tests covering extensive sets of man-made models with rich geometric and topological variations.

Category-specific features and valence in action-effect prediction: An EEG study

Despite extensive research on action-effect anticipation, little attention has been paid to the anticipation of different attributes of an event. An action-effect is not only a sensory event; it is often also an event of emotional value which can be pleasant or aversive. This latter attribute of action-effect prediction is similar to anticipation of reward versus punishment. To date the neural systems controlling sensory and reward anticipation have not been systematically compared. To this end, we designed an experiment to manipulate the sensory content and the emotional valence of the stimuli in an orthogonal fashion. We recorded and compared event-related potentials (ERPs) to the presentation of stimuli instantiating expected or unexpected features. Our results suggest (1) that both features are processed altogether and (2) that the prediction error resulting from the manipulation is reflected in an enhanced N400 component.

СПЕЦИФИКА ПРОВЕДЕНИЯ АНЕСТЕЗИИ У ДЕТЕЙ ПРИ ОПУХОЛЯХ ГОЛОВНОГО МОЗГА: СИСТЕМНЫЙ ОБЗОР

Aim. Based on publications dedicated to anesthetic management for surgery of children with brain neoplasms we aimed to reveal and summarize the specific features of anesthesia of such patients. Materials and Methods. We performed a systematic review and processed the information from Russian and foreign literature published in 2001–2016. The analysis included patients younger than 18 who had undergone surgical procedures due to brain tumor. Results. The conducted analysis allowed us to classify surgical interventions into three main categories (shunt surgery, open surgery, neuroendoscopy) and to determine category-specific features of anesthetic management. The analysis results also made it possible to describe the algorithms of preoperative preparation, recovery stage, and early postoperative period for anesthesiologist. Conclusion. The review has shown that brain tumor surgery is one of the most complicated operations requiring a well-coordinated teamwork. Anesthesiologist has not only to be especially well-trained and skilled, but to cooperate closely with neurosurgeon, which may be even more critical. Psychological, ethical, and professional aspects of such cooperation are a subject of further detailed research.

A life-long learning vector quantization approach for interactive learning of multiple categories

We present a new method capable of learning multiple categories in an interactive and life-long learning fashion to approach the "stability-plasticity dilemma". The problem of incremental learning of multiple categories is still largely unsolved. This is especially true for the domain of cognitive robotics, requiring real-time and interactive learning. To achieve the life-long learning ability for a cognitive system, we propose a new learning vector quantization approach combined with a category-specific feature selection method to allow several metrical "views" on the representation space of each individual vector quantization node. These category-specific features are incrementally collected during the learning process, so that a balance between the correction of wrong representations and the stability of acquired knowledge is achieved. We demonstrate our approach for a difficult visual categorization task, where the learning is applied for several complex-shaped objects rotated in depth.

Basic level scene categorization is affected by unrecognizable category-specific image features

Basic level scene categorization is affected by unrecognizable category-specific image features

Experience-dependent modulation of category-related cortical activity.

Naming pictures of objects from different categories (e.g. animals or tools) evokes maximal responses in different brain regions. However, these 'category-specific' regions typically respond to other object categories as well. Here we used stimulus familiarity to further investigate category representation. Naming pictures of animals and tools elicited category-related activity in a number of previously identified regions. This activity was reduced for familiar relative to novel stimuli. Reduced activation occurred in all object responsive areas in the ventral occipito-temporal cortex, regardless of which category initially produced the maximal response. This suggests that object representations in the ventral occipito-temporal cortex are not limited to a discrete area, but rather are widespread and overlapping. In other regions (e.g. the lateral temporal and left premotor cortices), experience-dependent reductions were category specific. Together, these findings suggest that category-related activations reflect the retrieval of information about category-specific features and attributes.

The impact of brand credibility on consumer price sensitivity

Brands can affect various stages of consumer choice processes, and hence, various components of consumer utility functions. Previous conceptual and empirical work focused on the effects of brands on consumer perceptions of tangible and intangible product attributes. In this paper, we extend the work on brand effects with information economics underpinnings to analyze whether consumer price sensitivity, that is, the weight attached to price in a consumer valuation of a product's overall attractiveness or utility, is impacted by brand credibility. In other words, we investigate how the impact of product price on consumer utility is moderated by brand credibility. To explore the impact of brand credibility on consumer price sensitivity across categories that may involve different levels of consumer uncertainty, we conduct our analysis for four products: frozen concentrate juice, jeans, shampoo and personal computers. These categories vary in the degree of potential consumer uncertainty about product attributes, as well as in a number of other category-specific features that may affect consumer sensitivity to uncertainty. Our results indicate that brand credibility decreases price sensitivity. Our results also indicate that although the direction of the impact is the same, the magnitude of brand credibility's impact on consumer choices and price sensitivity vary across product categories, as a function of product category characteristics that affect potential consumer uncertainty and consumer sensitivity to such uncertainty.