Author name cluster

Yao Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

BeyondSparse: Facilitating Mamba to Enhance Cross-Domain 3D Semantic Segmentation in Adverse Weather

Yao Wu
Mingwei Xing
Yachao Zhang
Fangyong Wang
Xiaopei Zhang
Yanyun Qu

Domain generalization (DG) and domain adaptation (DA) for 3D semantic segmentation enable the model to maintain high performance while avoiding labor-intensive and time-consuming annotation of target-domain data. However, under adverse weather conditions, the injection of spatial noise will affect the reflectivity of LiDAR point clouds, exacerbate domain distribution discrepancies, and degrade the generalization ability of the model. Current methods mainly rely on sparse convolution-based architecture. Due to its limited receptive field, the model captures varying local geometric information when dealing with point clouds of different sparsities, thereby limiting its transferability. To this end, we propose BeyondSparse, a novel cross-domain 3D semantic segmentation method under adverse weather that incorporates a state-space model into a 3D sparse convolution-based architecture, sequentially modeling all features to learn domain-invariant representations. This method consists of two main components: domain feature decoupling and Mamba-based encoder. The former performs feature disentanglement before sequential modeling, while the latter performs global modeling on voxelized point cloud data. In addition, we introduce a token-style augmentation to capture the intrinsic properties of input data. Extensive experimental results demonstrate that our method outperforms SOTA competitors in both DG and DA tasks, for instance, achieving +4.6% and +0.8% mIoU on ``SynLiDAR to SemanticSTF''.

PDF Details DOI

AAAI Conference 2026 Conference Paper

xMHashSeg: Cross-modal Hash Learning for Training-free Unsupervised LiDAR Semantic Segmentation

Jialong Zhang
Yachao Zhang
Yao Wu
Jiangming Shi
Fangyong Wang
Yanyun Qu

3D semantic segmentation serves as a fundamental component in many applications, such as autonomous driving and medical image analysis. Although recent methods have advanced the field, adapting these methods to new environments or object categories without extensive retraining remains a significant challenge. To address this, we introduce xMHashSeg, a novel training-free cross-modal LiDAR semantic segmentation framework. xMHashSeg leverages foundation models and non-parametric network to extract features from 2D images and 3D point clouds, subsequently integrating these features through hash learning. Specifically, We develop point-SANN, a novel self-adaption non-parametric network that can extract robust 3D features from raw point clouds, while 2D features are directly extracted through the foundation model DINOv2. To reconcile inconsistencies across different modals, we introduce a Hash Code Learning Module that projects all information into a common hash space, learning a consistent hash code that enhances feature integration. Additionally, depth maps are utilized as an intermediary form between 2D and 3D data to facilitate convergence during hash code learning. Our experimental results on various multi-modality datasets demonstrate that xMHashSeg outperforms zero-shot learning approaches and achieve performance close to that of unsupervised domain adaptation and test-time adaptation methods, without requiring any annotations or additional training.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Omni-Query Active Learning for Source-Free Domain Adaptive Cross-Modality 3D Semantic Segmentation

Jianxiang Xie
Yao Wu
Yachao Zhang
Zhongchao Shi
Jianping Fan
Yuan Xie
Yanyun Qu

Source-Free Domain Adaptation (SFDA) aims to transfer a pre-trained source model to the unlabeled target domain without accessing the source data, thereby effectively solving labeled data dependency and domain shift problems. However, the SFDA setting faces a bottleneck due to the absence of supervisory information. To mitigate this problem, Active Learning (AL) is introduced to combine with SFDA, endeavoring to actively label a small set of the most high-quality target points so that models with satisfactory performance can be obtained at an acceptable cost. Nevertheless, several issues remain unresolved, namely when to query new labels during training, what kind of samples deserve labeling to ensure rich information, and where the labels should be distributed to guarantee diversity. Thus we elaborate OmniQuery to omnibearing address the “When, What, and Where” problems about active points querying in source-free domain adaptation for cross-modal 3D semantic segmentation. The method consists of three main components: Query Decider, Point Ranker, and Budget Slicer. The Query Decider determines the optimal timing to query new points by fitting the validation curves during training. The Point Ranker nominates points for annotation by calculating the ambiguity of neighboring points in the feature space. The Budget Slicer allocates the annotation quota, i.e., labeling percentage of the point cloud, to different semantic regions by utilizing the advanced 2D semantic segmentation capabilities of the Segment Anything Model (SAM). Extensive experiments demonstrate the effectiveness of our proposed method, achieving up to 99.64% of fully supervised performance with only 3% of labels, and consistently outperforming comparison methods across various scenarios.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

CLIP-FSAC: Boosting CLIP for Few-Shot Anomaly Classification with Synthetic Anomalies

Zuo Zuo
Yao Wu
Baoqiang Li
Jiahao Dong
You Zhou
Lei Zhou
Yanyun Qu
Zongze Wu

Few-shot anomaly classification (FSAC) is a vital task in manufacturing industry. Recent methods focus on utilizing CLIP in zero/few normal shot anomaly detection instead of custom models. However, there is a lack of specific text prompts in anomaly classification and most of them ignore the modality gap between image and text. Meanwhile, there is distribution discrepancy between the pre-trained and the target data. To provide a remedy, in this paper, we propose a method to boost CLIP for few-normal-shot anomaly classification, dubbed CLIP-FSAC, which contains two-stage of training and alternating fine-tuning with two modality-specific adapters. Specifically, in the first stage, we train image adapter with text representation output from text encoder and introduce an image-to-text tuning to enhance multi-modal interaction and facilitate a better language-compatible visual representation. In the second stage, we freeze the image adapter to train the text adapter. Both of them are constrained by fusion-text contrastive loss. Comprehensive experiment results are provided for evaluating our method in few-normal-shot anomaly classification, which outperforms the state-of-the-art method by 12. 2%, 10. 9%, 10. 4% AUROC on VisA for 1, 2, and 4-shot settings.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Jie Han
Yixiong Zou
Haozhao Wang
Jun Wang
Wei Liu
Yao Wu
Tao Zhang
Ruixuan Li

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior

Yao Wu
Mingwei Xing
Yachao Zhang
Xiaotong Luo
Yuan Xie
Yanyun Qu

3D semantic segmentation using an adapting model trained from a source domain with or without accessing unlabeled target-domain data is the fundamental task in computer vision, containing domain adaptation and domain generalization. The essence of simultaneously solving cross-domain tasks is to enhance the generalizability of the encoder. In light of this, we propose a groundbreaking universal method with the help of off-the-shelf Visual Foundation Models (VFMs) to boost the adaptability and generalizability of cross-domain 3D semantic segmentation, dubbed $\textbf{UniDSeg}$. Our method explores the VFMs prior and how to harness them, aiming to inherit the recognition ability of VFMs. Specifically, this method introduces layer-wise learnable blocks to the VFMs, which hinges on alternately learning two representations during training: (i) Learning visual prompt. The 3D-to-2D transitional prior and task-shared knowledge is captured from the prompt space, and then (ii) Learning deep query. Spatial Tunability is constructed to the representation of distinct instances driven by prompts in the query space. Integrating these representations into a cross-modal learning framework, UniDSeg efficiently mitigates the domain gap between 2D and 3D modalities, achieving unified cross-domain 3D semantic segmentation. Extensive experiments demonstrate the effectiveness of our method across widely recognized tasks and datasets, all achieving superior performance over state-of-the-art methods. Remarkably, UniDSeg achieves 57. 5\%/54. 4\% mIoU on ``A2D2/sKITTI'' for domain adaptive/generalized tasks. Code is available at https: //github. com/Barcaaaa/UniDSeg.

PDF Details DOI

YNIMG Journal 2020 Journal Article

Altered local cerebellar and brainstem development in preterm infants

Yao Wu
Catherine Stoodley
Marie Brossard-Racine
Kushal Kapse
Gilbert Vezina
Jonathan Murnick
Adré J. du Plessis
Catherine Limperopoulos

BACKGROUND: Premature birth is associated with high prevalence of neurodevelopmental impairments in surviving infants. The putative role of cerebellar and brainstem dysfunction remains poorly understood, particularly in the absence of overt structural injury. METHOD: We compared in-utero versus ex-utero global, regional and local cerebellar and brainstem development in healthy fetuses (n = 38) and prematurely born infants without evidence of structural brain injury on conventional MRI studies (n = 74) that were performed at two time points: the first corresponding to the third trimester, either in utero or ex utero in the early postnatal period following preterm birth (30-40 weeks of gestation; 38 control fetuses; 52 premature infants) and the second at term equivalent age (37-46 weeks; 38 control infants; 58 premature infants). We compared 1) volumetric growth of 7 regions in the cerebellum (left and right hemispheres, left and right dentate nuclei, and the anterior, neo, and posterior vermis); 2) volumetric growth of 3 brainstem regions (midbrain, pons, and medulla); and 3) shape development in the cerebellum and brainstem using spherical harmonic description between the two groups. RESULTS: Both premature and control groups showed regional cerebellar differences in growth rates, with the left and right cerebellar hemispheres showing faster growth compared to the vermis. In the brainstem, the pons grew faster than the midbrain and medulla in both prematurely born infants and controls. Using shape analyses, premature infants had smaller left and right cerebellar hemispheres but larger regional vermis and paravermis compared to in-utero control fetuses. For the brainstem, premature infants showed impaired growth of the superior surface of the midbrain, anterior surface of the pons, and inferior aspects of the medulla compared to the control fetuses. At term-equivalent age, premature infants had smaller cerebellar hemispheres bilaterally, extending to the superior aspect of the left cerebellar hemisphere, and larger anterior vermis and posteroinferior cerebellar lobes than healthy newborns. For the brainstem, large differences between premature infants and healthy newborns were found in the anterior surface of the pons. CONCLUSION: This study analyzed both volumetric growth and shape development of the cerebellum and brainstem in premature infants compared to healthy fetuses using longitudinal MRI measurements. The findings in the present study suggested that preterm birth may alter global, regional and local development of the cerebellum and brainstem even in the absence of structural brain injury evident on conventional MRI.

Details DOI

YNIMG Journal 2014 Journal Article

Brain extraction based on locally linear representation-based classification

Meiyan Huang
Wei Yang
Jun Jiang
Yao Wu
Yu Zhang
Wufan Chen
Qianjin Feng

Brain extraction is an important procedure in brain image analysis. Although numerous brain extraction methods have been presented, enhancing brain extraction methods remains challenging because brain MRI images exhibit complex characteristics, such as anatomical variability and intensity differences across different sequences and scanners. To address this problem, we present a Locally Linear Representation-based Classification (LLRC) method for brain extraction. A novel classification framework is derived by introducing the locally linear representation to the classical classification model. Under this classification framework, a common label fusion approach can be considered as a special case and thoroughly interpreted. Locality is important to calculate fusion weights for LLRC; this factor is also considered to determine that Local Anchor Embedding is more applicable in solving locally linear coefficients compared with other linear representation approaches. Moreover, LLRC supplies a way to learn the optimal classification scores of the training samples in the dictionary to obtain accurate classification. The International Consortium for Brain Mapping and the Alzheimer's Disease Neuroimaging Initiative databases were used to build a training dataset containing 70 scans. To evaluate the proposed method, we used four publicly available datasets (IBSR1, IBSR2, LPBA40, and ADNI3T, with a total of 241 scans). Experimental results demonstrate that the proposed method outperforms the four common brain extraction methods (BET, BSE, GCUT, and ROBEX), and is comparable to the performance of BEaST, while being more accurate on some datasets compared with BEaST.

Details DOI

LPAR Conference 2005 Conference Paper

Computational Issues in Exploiting Dependent And-Parallelism in Logic Programming: Leftness Detection in Dynamic Search Trees

Yao Wu
Enrico Pontelli
Desh Ranjan

Abstract We present efficient Pure Pointer Machine (PPM) algorithms to test for “leftness” in dynamic search trees and related problems. In particular, we show that the problem of testing if a node x is in the leftmost branch of the subtree rooted in node y, in a dynamic tree that grows and shrinks at the leaves, can be solved on PPMs in worst-case O ((lg lg n ) 2 ) time per operation in the semi-dynamic case—i. e. ,all the operations that add leaves to the tree are performed before any other operations—where n is the number of operations that affect the structure of the tree. We also show that the problem can be solved on PPMs in amortized O ((lg lg n ) 2 ) time per operation in the fully dynamic case.

Details