Perceptual Boundaries Research Articles

Multi-Modal LiDAR Point Cloud Semantic Segmentation with Salience Refinement and Boundary Perception

Point cloud segmentation is essential for scene understanding, which provides advanced information for many applications, such as autonomous driving, robots, and virtual reality. To improve the accuracy and robustness of point cloud segmentation, many researchers have attempted to fuze camera images to complement the color and texture information. The common fusion strategy is the combination of convolutional operations with concatenation, element-wise addition or element-wise multiplication. However, conventional convolutional operators tend to confine the fusion of modal features within their receptive fields, which can be incomplete and limited. In addition, the inability of encoder–decoder segmentation networks to explicitly perceive segmentation boundary information results in semantic ambiguity and classification errors at object edges. These errors are further amplified in point cloud segmentation tasks, significantly affecting the accuracy of point cloud segmentation. To address the above issues, we propose a novel self-attention multi-modal fusion semantic segmentation network for point cloud semantic segmentation. Firstly, to effectively fuze different modal features, we propose a self-cross fusion module (SCF), which models long-range modality dependencies and transfers complementary image information to the point cloud to fully leverage the modality-specific advantages. Secondly, we design the salience refinement module (SR), which calculates the importance of channels in the feature maps and global descriptors to enhance the representation capability of salient modal features. Finally, we propose the local-aware anisotropy loss measure the element-level importance in the data and explicitly provide boundary information for the model, which alleviates the inherent semantic ambiguity problem in segmentation networks. Extensive experiments on two benchmark datasets demonstrate that our proposed method surpasses current state-of-the-art methods.

Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network

Early diagnosis and treatment of colorectal polyps are crucial for preventing colorectal cancer. This paper proposes a lightweight convolutional neural network for the automatic detection and auxiliary diagnosis of colorectal polyps. Initially, a 53-layer convolutional backbone network is used, incorporating a spatial pyramid pooling module to achieve feature extraction with different receptive field sizes. Subsequently, a feature pyramid network is employed to perform cross-scale fusion of feature maps from the backbone network. A spatial attention module is utilized to enhance the perception of polyp image boundaries and details. Further, a positional pattern attention module is used to automatically mine and integrate key features across different levels of feature maps, achieving rapid, efficient, and accurate automatic detection of colorectal polyps. The proposed model is evaluated on a clinical dataset, achieving an accuracy of 0.9982, recall of 0.9988, F1 score of 0.9984, and mean average precision (mAP) of 0.9953 at an intersection over union (IOU) threshold of 0.5, with a frame rate of 74 frames per second and a parameter count of 9.08 M. Compared to existing mainstream methods, the proposed method is lightweight, has low operating configuration requirements, high detection speed, and high accuracy, making it a feasible technical method and important tool for the early detection and diagnosis of colorectal cancer.

Congested traffic patterns of mixed lattice hydrodynamic model combining the perceptual range differences with passing effect

With the aid of Vehicle-to-everything (V2X) technologies for network connectivity, connected autonomous vehicles (CAVs) can broaden the drivers' perceptual boundaries and receive a greater quantity of exogenous vehicle information, thereby governing the vehicle's acceleration information of the next moment. Nonetheless, constrained by contemporary communication networks and sophisticated vehicle control technology, the process of promoting CAVs is long-lasting, and throughout this stage of transition, both CAVs and human-driven vehicles (HDVs) will happen on the road. Moreover, passing behaviour is uncommon in the traffic flow model despite being a fundamental microscopic driving behaviour, particularly within mixed-traffic situations. To bridge that hole, we introduce the percentage ratios of CAVs into the lattice hydrodynamic model by integrating the perceptual range differences between two different types of vehicles with passing effects. Subsequently, the stability norm associated with the new model is ascertained by performing the linear stability analysis. When the above-mentioned stability condition is not achieved, we investigate the complex behaviour of the new model, and the associated existing conditions, as well as the modified Korteweg-de Vries (mKdV) equation, are determined simultaneously. When the passing ratio is inadequate, no jam and kink jam make up the whole phase region; while when the passing ratio surpasses the minimum, the initial unstable region can be segregated into two extra segments: the chaotic sub-region and the kink jam sub-region, the density wave progressively transitioned from being a kink-Bando traffic wave to a chaotic phase. Lastly, the findings of the numerical experiment identify with the theoretical derivation made above.

Breaking (musical) boundaries by investigating brain dynamics of event segmentation during real-life music-listening

The perception of musical phrase boundaries is a critical aspect of human musical experience: It allows us to organize, understand, derive pleasure from, and remember music. Identifying boundaries is a prerequisite for segmenting music into meaningful chunks, facilitating efficient processing and storage while providing an enjoyable, fulfilling listening experience through the anticipation of upcoming musical events. Expanding on Sridharan et al.'s [Neuron 55, 521-532 (2007)] work on coarse musical boundaries between symphonic movements, we examined finer-grained boundaries. We measured the fMRI responses of 18 musicians and 18 nonmusicians during music listening. Using general linear model, independent component analysis, and Granger causality, we observed heightened auditory integration in anticipation to musical boundaries, and an extensive decrease within the fronto-temporal-parietal network during and immediately following boundaries. Notably, responses were modulated by musicianship. Findings uncover the intricate interplay between musical structure, expertise, and cognitive processing, advancing our knowledge of how the brain makes sense of music.

SAM-RSP: A new few-shot segmentation method based on segment anything model and rough segmentation prompts

Few-shot segmentation (FSS) aims to segment novel classes with a few labeled images. The backbones used in existing methods are pre-trained through classification tasks on the ImageNet dataset. Although these backbones can effectively perceive the semantic categories of images, they cannot accurately perceive the regional boundaries within one image, which limits the model performance. Recently, Segment Anything Model (SAM) has achieved precise image segmentation based on point or box prompts, thanks to its excellent perception of region boundaries within one image. However, it cannot effectively provide semantic information of images. This paper proposes a new few-shot segmentation method that can effectively perceive both semantic categories and regional boundaries. This method first utilizes the SAM encoder to perceive regions and obtain the query embedding. Then the support and query images are input into a backbone pre-trained on ImageNet to perceive semantics and generate a rough segmentation prompt (RSP). This query embedding is combined with the prompt to generate a pixel-level query prototype, which can better match the query embedding. Finally, the query embedding, prompt, and prototype are combined and input into the designed multi-layer prompt transformer decoder, which is more efficient and lightweight, and can provide a more accurate segmentation result. In addition, other methods can be easily combined with our framework to improve their performance. Plenty of experiments on PASCAL-5i and COCO-20i under 1-shot and 5-shot settings prove the effectiveness of our method. Our method also achieves new state-of-the-art. Codes are available at https://github.com/Jiaguang-NEU/SAM-RSP.

INA-Net: An integrated noise-adaptive attention neural network for enhanced medical image segmentation

Skin cancer, a growing health concern, poses a significant threat. Automated segmentation of skin lesions is crucial for precise clinical diagnosis and treatment. However, challenges such as hair interference, vascular occlusion, and ambiguous lesion boundaries in dermoscopic images complicate accurate segmentation. Recent research has focused on capturing multiscale-enhanced global information across spatial and channel dimensions to improve the segmentation of ambiguous boundaries. Despite these advancements, performance remains suboptimal in the presence of complex disturbances. To address this, we propose INA-Net, an Integrated Noise-Adaptive Attention Neural Network for enhanced medical image segmentation. INA-Net proposes a lightweight noise-range attention module that integrates local and simulated noise features with global information to improve robustness against complex mixed noises. Additionally, our proposed Edge-aware Spatial Attention (ESA) and Multi-scale Channel Attention (MCA) enhance feature information and boundary perception. The proposed Dynamic Noise Encoding module and Fourier Wavelet Analysis (FW-Parser) further improve robustness by handling high-frequency noise components. INA-Net effectively manages hair interference, vascular occlusion, and ambiguous lesion boundaries, thereby providing critical support for accurate lesion identification. Evaluations on the ISIC2016, ISIC2018, and PH2 datasets demonstrate outstanding performance, with IOU scores of 87.53%, 84.74%, and 85.30%, respectively. These results surpass those of other models with comparable complexity and size.

Boundary-Aware Gradient Operator Network for Medical Image Segmentation.

Medical image segmentation is a crucial task in computer-aided diagnosis. Although convolutional neural networks (CNNs) have made significant progress in the field of medical image segmentation, the convolution kernels of CNNs are optimized from random initialization without explicitly encoding gradient information, leading to a lack of specificity for certain features, such as blurred boundary features. Furthermore, the frequently applied down-sampling operation also loses the fine structural features in shallow layers. Therefore, we propose a boundary-aware gradient operator network (BG-Net) for medical image segmentation, in which the gradient convolution (GConv) and the boundary-aware mechanism (BAM) modules are developed to simulate image boundary features and the remote dependencies between channels. The GConv module transforms the gradient operator into a convolutional operation that can extract gradient features; it attempts to extract more features such as images boundaries and textures, thereby fully utilizing limited input to capture more features representing boundaries. In addition, the BAM can increase the amount of global contextual information while suppressing invalid information by focusing on feature dependencies and the weight ratios between channels. Thus, the boundary perception ability of BG-Net is improved. Finally, we use a multi-modal fusion mechanism to effectively fuse lightweight gradient convolution and U-shaped branch features into a multilevel feature, enabling global dependencies and low-level spatial details to be effectively captured in a shallower manner. We conduct extensive experiments on eight datasets that broadly cover medical images to evaluate the effectiveness of the proposed BG-Net. The experimental results demonstrate that BG-Net outperforms the state-of-the-art methods, particularly those focused on boundary segmentation.

Optimizing Slender Target Detection in Remote Sensing with Adaptive Boundary Perception

Optimizing Slender Target Detection in Remote Sensing with Adaptive Boundary Perception

In the eye of the beholder: national boundary perceptions and their identity implications across immigrant generations in multinational states

ABSTRACT The concept of national boundaries has been employed extensively in the social sciences, with most research focusing on the host society's perspective. This study innovates by measuring immigrants’ perceptions of how boundaries of their host nation are drawn and examining how such perceptions impact their national identifications in a multinational context, more specifically in the province of Quebec in Canada. It relies on a stratified sample of first- (n = 1129) and second-generation immigrants (n = 1286) as well as non-immigrants (n = 1472). We show that boundary perceptions impact the availability and attractiveness of different identity options, including identification with Quebec, the country of origin, and Canada. First, while perceptions of ascriptive boundaries to Quebec push first- and second-generation immigrants away from Quebec identity, the reactive effect of strengthening identification with the country of origin and Canada is limited. Second, although the second generation perceives Quebec boundaries as more ascriptive than the first generation, it is not more strongly impacted by their boundary perceptions in their identifications. Third, perceptions of attainable boundaries promote all three national identifications, but only for the first generation. Finally, we demonstrate that attention to boundary perceptions adds important explanatory leverage beyond the impact that discrimination has on national identifications.

Event boundary perception in audio described films by people without sight

AbstractAudio description (AD) plays a crucial role in making audiovisual media accessible to people with a visual impairment, enhancing their experience and understanding. This study employs an event segmentation task to examine how people without sight perceive and segment narrative events in films with AD, compared to sighted viewers without AD. Two AD versions were utilized, differing in the explicitness of conveyed event boundaries. Results reveal that the participants without sight generally perceived event boundaries similarly to their sighted peers, affirming AD's effectiveness in conveying event structures. However, when key event boundaries were more implicitly expressed, event boundary recognition diminished. Collectively, these findings offer valuable insights into event segmentation processes across sensory modalities. Additionally, they underscore the significance of how AD presents event boundaries, influencing the perception and interpretation of audiovisual media for people with a visual impairment and providing applied insights into event segmentation, multimodal processing, and audiovisual accessibility.

Assessing the unseen consequences: influence of an extreme weather event on environmental perceptions and connection to nature

BackgroundDue to climate change, extreme weather events are becoming more frequent worldwide. An example of such an extreme weather event was the flooding in Western Europe in July 2021. Currently, there are large research gaps regarding how such events, particularly those involving oil pollution, affect people's connection to nature and their perceptions of environmental problems. Perceptions and connections to nature are important factors that influence environmental behavior and decisions. This study examines the influence of the exposure of oil pollution during the 2021 floods on the perception of the natural environment (connection to nature) and of environmental problems (perception of planetary boundaries). To this end, people affected by flooding who have come into direct or indirect contact with oil pollution are examined, with people from unaffected regions serving as a control group.ResultsNo significant differences were found for both the connection to nature and the perception of planetary boundaries between the three groups studied. Connection to nature was at a moderate level in all three groups. In the case of planetary boundaries, it was observed that all boundaries were rated as significantly exceeded in all three groups. Especially the boundary of novel entities to which also oil pollution belongs, was evaluated as highly exceeded.ConclusionsThe results suggest that extreme weather events do not negatively impact personal connection to nature. Additionally, no significant group differences were found in the assessment of planetary boundaries, which may be attributed to the inherently high assessment scores in Germany. The study provides evidence that perceptions of environmental problems and connection to nature are relatively stable in the face of an extreme weather event with a natural trigger. Further studies are needed to investigate the reasons and consequences of this stability.

Attention-Based Multi-Kernelized and Boundary-Aware Network for image semantic segmentation

Recent studies have witnessed the prosperity of image semantic segmentation brought by deep learning technology, including the integration of diverse network structures, attention mechanisms, and even boundary perception. Essentially, the main challenge of semantic segmentation lies in how to incorporate and align more information like contexts and details in the feature representation enabling the network to better distinguish and recognize objects in an image for improved semantic understanding. To this end, we propose a novel end-to-end deep framework termed Attention-Based Multi-Kernelized and Boundary-Aware Network to enhance the semantic segmentation performance. Specifically, the proposed network enables thoroughly exploring and engaging the multi-kernelized contextual information with high-frequency boundary information by applying novel modules of Multi-Kernelized Spatial Attention and Boundary-Aware Hybrid Attention, aiming to enhance the segmentation result with more comprehensive feature representation capability. Extensive experiments further consolidate the superiority of the proposed network with improved segmentation results with the mIoU of 51.1% and 82.9% on ADE20K and Cityscapes datasets, as well as classification results with Top-1 accuracy of 84.0% on ImageNet-1K dataset against competitive baselines.

Low-Contrast Medical Image Segmentation via Transformer and Boundary Perception

Low-Contrast Medical Image Segmentation via Transformer and Boundary Perception

Space and perceptual boundaries

In consideration of the spatial structures of sensory experiences, an ‘Externality Thesis’ is commonly proposed, according to which awareness of sensory boundaries is also an awareness of the presence of a space beyond these boundaries. The paper evaluates the Externality Thesis in the context of vision and touch. More specifically, relying on mereotopological theories, it is shown that the notion of spatial boundaries is ambiguous as it encompasses various distinct ways in which entities may be connected by a boundary. It is argued that only some of these ways are able to support the Externality Thesis. In particular, it is claimed that while bodily boundaries of which one is aware in tactile sensations are such that the awareness of them provides support for the Externality Thesis, the analogous claim is not true about the boundaries of the visual field.

Remote sensing image semantic segmentation via class-guided structural interaction and boundary perception

Existing remote sensing semantic segmentation methods generally ignore the structural information of objects that is vital in the human visual recognition system. The absence of overall structural information often results in weak perceptions of subtle textures and fragmented predictions, especially for complex and variable ground object scenarios. Besides, they still suffer from the semantic ambiguity caused by the unclear object boundary features in remote sensing images. In this paper, we propose a novel remote sensing semantic segmentation framework, called CSBNet, which aims to enhance the capacity of class-guided structural interaction and boundary perception simultaneously. It consists of a class-guided structure interaction module (CSIM), a Transformer-based context aggregation module (TCAM) and a class-guided boundary supervision module (CBSM). The CSIM has the ability to progressively extract the class-specific structural features, i.e., refining the structural information of each class by iteratively exchanging information between initial coarse class tokens and contexts. Meanwhile, the TCAM is constructed to provide CSIM with more discriminative multi-scale contexts without losing spatial features. In particular, the CBSM plays an auxiliary role, which applies the boundary information obtained from the class tokens to supervise the segmentation of boundary regions. When tested on the ISPRS dataset, LoveDA dataset, UAVid dataset, our method significantly outperforms the state-of-the-art remote sensing semantic segmentation approaches.

Impact of speech rate on perception of vowel and consonant duration by bilinguals and monolinguals.

The perceptual boundary between short and long categories depends on speech rate. We investigated the influence of speech rate on perceptual boundaries for short and long vowel and consonant contrasts by Spanish-English bilingual listeners and English monolinguals. Listeners tended to adapt their perceptual boundaries to speech rates, but the strategy differed between groups, especially for consonants. Understanding the factors that influence auditory processing in this population is essential for developing appropriate assessments of auditory comprehension. These findings have implications for the clinical care of older populations whose ability to rely on spectral and/or temporal information in the auditory signal may decline.

SBCNet: Scale and Boundary Context Attention Dual-Branch Network for Liver Tumor Segmentation.

Automated segmentation of liver tumors in CT scans is pivotal for diagnosing and treating liver cancer, offering a valuable alternative to labor-intensive manual processes and ensuring the provision of accurate and reliable clinical assessment. However, the inherent variability of liver tumors, coupled with the challenges posed by blurred boundaries in imaging characteristics, presents a substantial obstacle to achieving their precise segmentation. In this paper, we propose a novel dual-branch liver tumor segmentation model, SBCNet, to address these challenges effectively. Specifically, our proposed method introduces a contextual encoding module, which enables a better identification of tumor variability using an advanced multi-scale adaptive kernel. Moreover, a boundary enhancement module is designed for the counterpart branch to enhance the perception of boundaries by incorporating contour learning with the Sobel operator. Finally, we propose a hybrid multi-task loss function, concurrently concerning tumors' scale and boundary features, to foster interaction across different tasks of dual branches, further improving tumor segmentation. Experimental validation on the publicly available LiTS dataset demonstrates the practical efficacy of each module, with SBCNet yielding competitive results compared to other state-of-the-art methods for liver tumor segmentation.

Age effects on prosodic boundary perception.

The redundancy hypothesis proposes that older listeners need a larger array of acoustic cues than younger listeners for effective speech perception. This research investigated this hypothesis by examining the aging effects on the use of prosodic cues in speech segmentation in Mandarin Chinese. We examined how younger and older listeners perceived prosodic boundaries using three main prosodic cues (pause, final lengthening, and pitch change) across eight conditions involving different cue combinations. The stimuli consisted of syntactically ambiguous phrase pairs, each containing two or three objects. Participants (22 younger listeners and 22 older listeners) performed a speech recognition task to judge the number of objects they heard. Both groups primarily relied on the pause cue for identifying prosodic boundaries, using final lengthening and pitch change as secondary cues. However, older listeners showed reduced sensitivity to these cues, compensating by integrating the primary cue pause with the secondary cue pitch change for more precise segmentation. The present study reveals older listeners' integration strategy in using prosodic cues for speech segmentation, supporting the redundancy hypothesis. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Succeeding without belonging? A double comparison of migrants’ socio-economic attainment and national belonging across origin and residence countries

Abstract When is migrants’ socio-economic attainment associated with enhanced national belonging to their residence country? Drawing on a large-scale survey, we compare migrants from the same 10 origin countries across Denmark, Germany, and the Netherlands. We exploit this double comparison across origin groups and residence countries to contextualize mixed findings of positive, negative, and null associations between migrants’ socio-economic attainment and national belonging in earlier research. We introduce the notion of ethnic boundaries to situate when migrants’ socio-economic attainment and belonging are positively or negatively associated. We examine how migrants’ socio-economic attainment interacts with contextual variation in ethnic boundaries and with individual-level variation in perceptions of ethnic boundaries based on perceived group discrimination. Multi-group structural equation models show that migrants’ socio-economic attainment is often decoupled from national belonging. However, they also reveal crucial contextual variation as same-origin migrants can succeed socio-economically with or without feeling belonging in different residence countries. At the individual level, perceived group discrimination conditions this association, so that socio-economic attainment translates into more national belonging only when perceptions of discrimination are low. Our comparative findings of contingent national belonging thereby challenge existing assumptions that associations between socio-economic attainment and national belonging are linear and that ethnic boundaries in European migration contexts are rigid.

Cross co-teaching for semi-supervised medical image segmentation

Excellent performance has been achieved on semi-supervised medical image segmentation, but existing algorithms perform relatively poorly for objects with variable topologies and weak boundaries. In this paper, we propose a novel cross co-teaching framework, called Cross-structure-task Collaborative Teaching (CroCT), which not only can effectively handle variable topologies, but also strengthens the learning for weak boundaries of unlabeled data. Specifically, a new cross-structure-task collaborative teaching mechanism is developed based on our designed “E-Net” structure composed of a shared encoder and two decoder branches with distinct learning paradigms, which asks these two branches to regress topology-aware signed distance functions and densely-predicted segmentation masks for each other. Powered by the collaboration across different structural biases and sequence-related tasks, our CroCT can extract more discriminative yet complementary representations from abundant raw medical data to promote the consistency learning generalization, further boosting the performance for tackling highly diverse shapes and topological changes intra-/inter-slices. Besides, it guarantees the diversities from multi-levels, i.e., structure and task perspectives, to preclude prediction uncertainty. In addition, a novel adaptive boundary enhancing (ABE) module is proposed to introduce compact annularly enhanced boundary features into semi-supervised training, which significantly improves weak boundary perception ability for unlabeled data while facilitating collaborative teaching for efficiently propagating complementary knowledge across different branches. The extensive experiments on three challenging medical benchmarks, employing different labeled settings, demonstrate the superiority of our CroCT over recent state-of-the-art competitors.