Xing Wei

AAAI Conference 2026 Conference Paper

Edge Self-Adversarial Augmentation Enhances Graph Contrastive Learning Against Neighborhood Inconsistency

• Chunchun Chen
• Xing Wei
• Jiayi Yang
• Chenrun Wang
• Yiwei Fu
• Yuxing Zhang
• Xin Sun
• Rui Fan

Recent studies have shown that unsupervised graph contrastive learning (GCL) is vulnerable to adversarial attacks. Automatic adversarial augmentation techniques are proposed to improve both the effectiveness and robustness of GCL. Existing methods typically regard unsupervised contrastive loss as the adversarial goal, essentially aiming to maximize inter-view instance-wise discrepancies between adversarial and original views. However, such attacks overlook intra-view neighborhood inconsistency, which hinders the robustness of GCL models against local neighborhood noises, resulting in performance degradation on low-homophily graphs. To tackle this issue, we propose a novel adversarial contrastive paradigm, named Edge self-aDversarial Augmentation for Graph Contrastive Learning (EDA-GCL). We theoretically establish that the adversarial objective of the intra-view neighborhood is equivalent to maximizing the discrepancy between bidirectional edge features. Hence, we build our adversarial framework based on edge self-adversarial learning. It generates pairwise adversarial augmentations from the original view by learning distinct neighborhood connectivity structures. The learned pairwise adversarial views are utilized for GCL model training in the minimization stage. Notably, this edge-level adversarial approach reduces the computational complexity to the level of the edge number. Experiments on various graph tasks and complex noise scenarios demonstrate the superiority and robustness of our EDA-GCL.

AAAI Conference 2026 Conference Paper

Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving

• Shiyi Liang
• Xinyuan Chang
• Changjie Wu
• Huiyuan Yan
• Yifan Bai
• Xinran Liu
• Hang Zhang
• Yujian Yuan

Safe autonomous driving requires both accurate HD map construction and persistent awareness of traffic rules, even when their associated signs are no longer visible. However, existing methods either focus solely on geometric elements or treat rules as temporary classifications, failing to capture their persistent effectiveness across extended driving sequences. In this paper, we present PAMR (Persistent Autoregressive Mapping with Traffic Rules), a novel framework that performs autoregressive co-construction of lane vectors and traffic rules from visual observations. Our approach introduces two key mechanisms: Map-Rule Co-Construction for processing driving scenes in temporal segments, and Map-Rule Cache for maintaining rule consistency across these segments. To properly evaluate continuous and consistent map generation, we develop MapDRv2, featuring improved lane geometry annotations. Extensive experiments demonstrate that PAMR achieves superior performance in joint vector-rule mapping tasks, while maintaining persistent rule effectiveness throughout extended driving sequences.

AAAI Conference 2026 Conference Paper

PriorDrive: Enhancing Online HD Mapping with Unified Vector Priors

• Shuang Zeng
• Xinyuan Chang
• Xinran Liu
• Yujian Yuan
• Shiyi Liang
• Zheng Pan
• Mu Xu
• Xing Wei

High-Definition Maps (HD maps) are essential for the precise navigation and decision-making of autonomous vehicles, yet their creation and upkeep present significant cost and timeliness challenges. The online construction of HD maps using on-board sensors has emerged as a promising solution; however, these methods can be impeded by incomplete data due to occlusions and inclement weather, while their performance in distant regions remains unsatisfying. This paper proposes PriorDrive to address these limitations by directly harnessing the power of various vectorized prior maps, significantly enhancing the robustness and accuracy of online HD map construction. Our approach integrates a variety of prior maps uniformly, such as OpenStreetMap's Standard Definition Maps (SD maps), outdated HD maps from vendors, and locally constructed maps from historical vehicle data. To effectively integrate such prior information into online mapping models, we introduce a Hybrid Prior Representation (HPQuery) that standardizes the representation of diverse map elements. We further propose a Unified Vector Encoder (UVE), which employs fused prior embedding and a dual encoding mechanism to encode vector data. To improve the UVE's generalizability and performance, we propose a segment-level and point-level pre-training strategy that enables the UVE to learn the prior distribution of vector data. Through extensive testing on the nuScenes, Argoverse 2 and OpenLane-V2, we demonstrate that PriorDrive is highly compatible with various online mapping models and substantially improves map prediction capabilities. The integration of prior maps through PriorDrive offers a robust solution to the challenges of single-perception data, paving the way for more reliable autonomous driving.

NeurIPS Conference 2025 Conference Paper

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving

• Shuang Zeng
• Xinyuan Chang
• Mengwei Xie
• Xinran Liu
• Yifan Bai
• Zheng Pan
• Mu Xu
• Xing Wei

Vision–Language–Action (VLA) models are increasingly used for end-to-end driving due to their world knowledge and reasoning ability. Most prior work, however, inserts textual chains-of-thought (CoT) as intermediate steps tailored to the current scene. Such symbolic compressions can blur spatio-temporal relations and discard fine visual cues, creating a cross-modal gap between perception and planning. We propose FSDrive, a visual spatio-temporal CoT framework that enables VLAs to think in images. The model first acts as a world model to generate a unified future frame that overlays coarse but physically-plausible priors—future lane dividers and 3D boxes—on the predicted future image. This unified frame serves as the visual CoT, capturing both spatial structure and temporal evolution. The same VLA then functions as an inverse-dynamics model, planning trajectories from current observations and the visual CoT. To equip VLAs with image generation while preserving understanding, we introduce a unified pre-training paradigm that expands the vocabulary to include visual tokens and jointly optimizes VQA (for semantics) and future-frame prediction (for dynamics). A progressive easy-to-hard scheme first predicts lane/box priors to enforce physical constraints, then completes full future frames for fine details. On nuScenes and NAVSIM, FSDrive improves trajectory accuracy and reduces collisions under both ST-P3 and UniAD metrics, and attains competitive FID for future-frame generation despite using lightweight autoregression. It also advances scene understanding on DriveLM. Together, these results indicate that visual CoT narrows the cross-modal gap and yields safer, more anticipatory planning. Code is available at https: //github. com/MIV-XJTU/FSDrive.

EAAI Journal 2025 Journal Article

Multi-scale pseudo-labels filtering and key pixels adversarial alignment for domain adaptive object detection

• Xing Wei
• Jiong Xia
• Fan Yang
• Chong Zhao
• Cang Liu
• Ge Wang
• Yanke Chen
• Yang Lu

Domain Adaptive Object Detection (DAOD) aims to adapt a detector trained on the labeled source domain to perform effectively on the unlabeled target domain. Most existing DAOD methods commonly employ self-training strategy and adversarial learning. However, the methods based on the self-training strategy often generate unreliable pseudo-labels (e. g. , missing detections and false positives) due to the absence of target domain semantics, resulting in suboptimal models. Meanwhile, aligning a large number of unimportant pixels hampers adversarial learning’s ability to capture domain-invariant semantic information. Therefore, we propose the Multi-scale Adversarial Teacher Framework (MATF) based on the common self-training framework (teacher–student framework). Specifically, to mitigate the impact of unreliable pseudo-labels, we propose the Multi-scale Negatives Filtering (MNF) module in the teacher model, which prevents missing detections from damaging the model by filtering out unreliable negative samples at multiple feature scales. In addition, we propose the Multi-scale Key-Pixel Discriminator (MKPD), which predicts the distributions of key pixels at multiple feature scales emphasizing the adversarial alignment of key pixels rather than unimportant pixels. Finally, to generate higher-quality pseudo-labels, we introduce the discriminator into the student model to reduce the model’s bias towards the source domain. Unlike most methods, we construct our method on a computationally efficient but less work-intensive one-stage detector. Extensive experiments conducted on DAOD benchmark datasets such as Cityscapes, FoggyCityscapes, KITTI, and Sim10k demonstrate the strong adaptability and effectiveness of MATF.

NeurIPS Conference 2025 Conference Paper

Preference-driven Knowledge Distillation for Few-shot Node Classification

• Xing Wei
• Chunchun Chen
• Rui Fan
• Xiaofeng Cao
• Sourav Medya
• Wei Ye

Graph neural networks (GNNs) can efficiently process text-attributed graphs (TAGs) due to their message-passing mechanisms, but their training heavily relies on the human-annotated labels. Moreover, the complex and diverse local topologies of nodes of real-world TAGs make it challenging for a single mechanism to handle. Large language models (LLMs) perform well in zero-/few-shot learning on TAGs but suffer from a scalability challenge. Therefore, we propose a preference-driven knowledge distillation (PKD) framework to synergize the complementary strengths of LLMs and various GNNs for few-shot node classification. Specifically, we develop a GNN-preference-driven node selector that effectively promotes prediction distillation from LLMs to teacher GNNs. To further tackle nodes' intricate local topologies, we develop a node-preference-driven GNN selector that identifies the most suitable teacher GNN for each node, thereby facilitating tailored knowledge distillation from teacher GNNs to the student GNN. Extensive experiments validate the efficacy of our proposed framework in few-shot node classification on real-world TAGs. Our code can be available at.

AAAI Conference 2024 Conference Paper

Evolving Parameterized Prompt Memory for Continual Learning

• Muhammad Rifki Kurniawan
• Xiang Song
• Zhiheng Ma
• Yuhang He
• Yihong Gong
• Yang Qi
• Xing Wei

Recent studies have demonstrated the potency of leveraging prompts in Transformers for continual learning (CL). Nevertheless, employing a discrete key-prompt bottleneck can lead to selection mismatches and inappropriate prompt associations during testing. Furthermore, this approach hinders adaptive prompting due to the lack of shareability among nearly identical instances at more granular level. To address these challenges, we introduce the Evolving Parameterized Prompt Memory (EvoPrompt), a novel method involving adaptive and continuous prompting attached to pre-trained Vision Transformer (ViT), conditioned on specific instance. We formulate a continuous prompt function as a neural bottleneck and encode the collection of prompts on network weights. We establish a paired prompt memory system consisting of a stable reference and a flexible working prompt memory. Inspired by linear mode connectivity, we progressively fuse the working prompt memory and reference prompt memory during inter-task periods, resulting in continually evolved prompt memory. This fusion involves aligning functionally equivalent prompts using optimal transport and aggregating them in parameter space with an adjustable bias based on prompt node attribution. Additionally, to enhance backward compatibility, we propose compositional classifier initialization, which leverages prior prototypes from pre-trained models to guide the initialization of new classifiers in a subspace-aware manner. Comprehensive experiments validate that our approach achieves state-of-the-art performance in both class and domain incremental learning scenarios.

IJCAI Conference 2024 Conference Paper

ReliaAvatar: A Robust Real-Time Avatar Animator with Integrated Motion Prediction

• Bo Qian
• Zhenhuan Wei
• Jiashuo Li
• Xing Wei

Efficiently estimating the full-body pose with minimal wearable devices presents a worthwhile research direction. Despite significant advancements in this field, most current research neglects to explore full-body avatar estimation under low-quality signal conditions, which is prevalent in practical usage. To bridge this gap, we summarize three scenarios that may be encountered in real-world applications: standard scenario, instantaneous data-loss scenario, and prolonged data-loss scenario, and propose a new evaluation benchmark. The solution we propose to address data-loss scenarios is integrating the full-body avatar pose estimation problem with motion prediction. Specifically, we present ReliaAvatar, a real-time, reliable avatar animator equipped with predictive modeling capabilities employing a dual-path architecture. ReliaAvatar operates effectively, with an impressive performance rate of 109 frames per second (fps). Extensive comparative evaluations on widely recognized benchmark datasets demonstrate ReliaAvatar's superior performance in both standard and low data-quality conditions. The code is available at https: //github. com/MIV-XJTU/ReliaAvatar.

AAAI Conference 2023 Conference Paper

Fast and Accurate Binary Neural Networks Based on Depth-Width Reshaping

• Ping Xue
• Yang Lu
• Jingfei Chang
• Xing Wei
• Zhen Wei

Network binarization (i.e., binary neural networks, BNNs) can efficiently compress deep neural networks and accelerate model inference but cause severe accuracy degradation. Existing BNNs are mainly implemented based on the commonly used full-precision network backbones, and then the accuracy is improved with various techniques. However, there is a question of whether the full-precision network backbone is well adapted to BNNs. We start from the factors of the performance degradation of BNNs and analyze the problems of directly using full-precision network backbones for BNNs: for a given computational budget, the backbone of a BNN may need to be shallower and wider compared to the backbone of a full-precision network. With this in mind, Depth-Width Reshaping (DWR) is proposed to reshape the depth and width of existing full-precision network backbones and further optimize them by incorporating pruning techniques to better fit the BNNs. Extensive experiments demonstrate the analytical result and the effectiveness of the proposed method. Compared with the original backbones, the DWR backbones constructed by the proposed method result in close to O(√s) decrease in activations, while achieving an absolute accuracy increase by up to 1.7% with comparable computational cost. Besides, by using the DWR backbones, existing methods can achieve new state-of-the-art (SOTA) accuracy (e.g., 67.2% on ImageNet with ResNet-18 as the original backbone). We hope this work provides a novel insight into the backbone design of BNNs. The code is available at https://github.com/pingxue-hfut/DWR.

IJCAI Conference 2023 Conference Paper

Hyperspectral Image Denoising Using Uncertainty-Aware Adjustor

• Jiahua Xiao
• Xing Wei

Hyperspectral image (HSI) denoising has achieved promising results with the development of deep learning. A mainstream class of methods exploits the spatial-spectral correlations and recovers each band with the aids of neighboring bands, collectively referred to as spectral auxiliary networks. However, these methods treat entire adjacent spectral bands equally. In theory, clearer and nearer bands tend to contain more reliable spectral information than noisier and farther ones with higher uncertainties. How to achieve spectral enhancement and adaptation of each adjacent band has become an urgent problem in HSI denoising. This work presents the UA-Adjustor, a comprehensive adjustor that enhances denoising performance by considering both the band-to-pixel and enhancement-to-adjustment aspects. Specifically, UA-Adjustor consists of three stages that evaluate the importance of neighboring bands, enhance neighboring bands based on uncertainty perception, and adjust the weight of spatial pixels in adjacent bands through estimated uncertainty. For its simplicity, UA-Adjustor can be flexibly plugged into existing spectral auxiliary networks to improve denoising behavior at low cost. Extensive experimental results validate that the proposed solution can improve over recent state-of-the-art (SOTA) methods on both simulated and real-world benchmarks by a large margin.

NeurIPS Conference 2023 Conference Paper

Sparse Parameterization for Epitomic Dataset Distillation

• Xing Wei
• Anjia Cao
• Funing Yang
• Zhiheng Ma

The success of deep learning relies heavily on large and diverse datasets, but the storage, preprocessing, and training of such data present significant challenges. To address these challenges, dataset distillation techniques have been proposed to obtain smaller synthetic datasets that capture the essential information of the originals. In this paper, we introduce a Sparse Parameterization for Epitomic datasEt Distillation (SPEED) framework, which leverages the concept of dictionary learning and sparse coding to distill epitomes that represent pivotal information of the dataset. SPEED prioritizes proper parameterization of the synthetic dataset and introduces techniques to capture spatial redundancy within and between synthetic images. We propose Spatial-Agnostic Epitomic Tokens (SAETs) and Sparse Coding Matrices (SCMs) to efficiently represent and select significant features. Additionally, we build a Feature-Recurrent Network (FReeNet) to generate hierarchical features with high compression and storage efficiency. Experimental results demonstrate the superiority of SPEED in handling high-resolution datasets, achieving state-of-the-art performance on multiple benchmarks and downstream applications. Our framework is compatible with a variety of dataset matching approaches, generally enhancing their performance. This work highlights the importance of proper parameterization in epitomic dataset distillation and opens avenues for efficient representation learning. Source code is available at https: //github. com/MIV-XJTU/SPEED.

AAAI Conference 2022 Conference Paper

SOIT: Segmenting Objects with Instance-Aware Transformers

• Xiaodong Yu
• Dahu Shi
• Xing Wei
• Ye Ren
• Tingqun Ye
• Wenming Tan

This paper presents an end-to-end instance segmentation framework, termed SOIT, that Segments Objects with Instance-aware Transformers. Inspired by DETR, our method views instance segmentation as a direct set prediction problem and effectively removes the need for many hand-crafted components like RoI cropping, one-to-many label assignment, and non-maximum suppression (NMS). In SOIT, multiple queries are learned to directly reason a set of object embeddings of semantic category, bounding-box location, and pixel-wise mask in parallel under the global image context. The class and bounding-box can be easily embedded by a fixed-length vector. The pixel-wise mask, especially, is embedded by a group of parameters to construct a lightweight instance-aware transformer. Afterward, a fullresolution mask is produced by the instance-aware transformer without involving any RoI-based operation. Overall, SOIT introduces a simple single-stage instance segmentation framework that is both RoI- and NMS-free. Experimental results on the MS COCO dataset demonstrate that SOIT outperforms state-of-the-art instance segmentation approaches significantly. Moreover, the joint learning of multiple tasks in a unified query embedding can also substantially improve the detection performance. Code is available at https: //github. com/yuxiaodongHRI/SOIT.

IJCAI Conference 2021 Conference Paper

Direct Measure Matching for Crowd Counting

• Hui Lin
• Xiaopeng Hong
• Zhiheng Ma
• Xing Wei
• Yunfeng Qiu
• Yaowei Wang
• Yihong Gong

Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussian kernel sizes. In this paper, we propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly. First, crowd counting is formulated as a measure matching problem. Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching. Third, we propose a self-supervised mechanism by devising a Sinkhorn scale consistency loss to resist scale changes. Finally, an efficient optimization method is provided to minimize the overall loss function. Extensive experiments on four challenging crowd counting datasets namely ShanghaiTech, UCF-QNRF, JHU++ and NWPU have validated the proposed method.

AAAI Conference 2021 Conference Paper

Efficient Deep Image Denoising via Class Specific Convolution

• Lu Xu
• Jiawei Zhang
• Xuanye Cheng
• Feng Zhang
• Xing Wei
• Jimmy Ren

Deep neural networks have been widely used in image denoising during the past few years. Even though they achieve great success on this problem, they are computationally inefficient which makes them inappropriate to be implemented in mobile devices. In this paper, we propose an efficient deep neural network for image denoising based on pixel-wise classification. Despite using a computationally efficient network cannot effectively remove the noises from any content, it is still capable to denoise from a specific type of pattern or texture. The proposed method follows such a divide and conquer scheme. We first use an efficient U-net to pixel-wisely classify pixels in the noisy image based on the local gradient statistics. Then we replace part of the convolution layers in existing denoising networks by the proposed Class Specific Convolution layers (CSConv) which use different weights for different classes of pixels. Quantitative and qualitative evaluations on public datasets demonstrate that the proposed method can reduce the computational costs without sacrificing the performance compared to state-of-the-art algorithms.

AAAI Conference 2021 Conference Paper

Error-Aware Density Isomorphism Reconstruction for Unsupervised Cross-Domain Crowd Counting

• Yuhang He
• Zhiheng Ma
• Xing Wei
• Xiaopeng Hong
• Wei Ke
• Yihong Gong

This paper focuses on the unsupervised domain adaptation problem for video-based crowd counting, in which we use labeled data as source domain and unlabelled video data as target domain. It is challenging as there is a huge gap between the source and the target domain and no annotations of samples are available in the target domain. The key issue is how to utilize unlabelled videos in the target domain for knowledge learning and transferring from the source domain. To tackle this problem, we propose a novel Error-aware Density Isomorphism REConstruction Network (EDIREC-Net) for cross-domain crowd counting. EDIREC-Net jointly transfers a pre-trained counting model to target domains using a density isomorphism reconstruction objective and models the reconstruction erroneousness by error reasoning. Specifically, as crowd flows in videos are consecutive, the density maps in adjacent frames turn out to be isomorphic. On this basis, we regard the density isomorphism reconstruction error as a self-supervised signal to transfer the pre-trained counting models to different target domains. Moreover, we leverage an estimation-reconstruction consistency to monitor the density reconstruction erroneousness and suppress unreliable density reconstructions during training. Experimental results on four benchmark datasets demonstrate the superiority of the proposed method and ablation studies investigate the efficiency and robustness. The source code is available at https: //github. com/GehenHe/EDIREC-Net.

AAAI Conference 2021 Conference Paper

Few-Shot Class-Incremental Learning via Relation Knowledge Distillation

• Songlin Dong
• Xiaopeng Hong
• Xiaoyu Tao
• Xinyuan Chang
• Xing Wei
• Yihong Gong

In this paper, we focus on the challenging few-shot classincremental learning (FSCIL) problem, which requires to transfer knowledge from old tasks to new ones and solves catastrophic forgetting. We propose the exemplar relation distillation incremental learning framework to balance the tasks of old-knowledge preserving and new-knowledge adaptation. First, we construct an exemplar relation graph to represent the knowledge learned by the original network and update gradually for new tasks learning. Then an exemplar relation loss function for discovering the relation knowledge between different classes is introduced to learn and transfer the structural information in relation graph. A large number of experiments demonstrate that relation knowledge does exist in the exemplars and our approach outperforms other state-ofthe-art class-incremental learning methods on the CIFAR100, miniImageNet, and CUB200 datasets.

AAAI Conference 2021 Conference Paper

Learning to Count via Unbalanced Optimal Transport

• Zhiheng Ma
• Xing Wei
• Xiaopeng Hong
• Hui Lin
• Yunfeng Qiu
• Yihong Gong

Counting dense crowds through computer vision technology has attracted widespread attention. Most crowd counting datasets use point annotations. In this paper, we formulate crowd counting as a measure regression problem to minimize the distance between two measures with different supports and unequal total mass. Specifically, we adopt the unbalanced optimal transport distance, which remains stable under spatial perturbations, to quantify the discrepancy between predicted density maps and point annotations. An efficient optimization algorithm based on the regularized semidual formulation of UOT is introduced, which alternatively learns the optimal transportation and optimizes the density regressor. The quantitative and qualitative results illustrate that our method achieves state-of-the-art counting and localization performance.

AAAI Conference 2020 Conference Paper

Infrared-Visible Cross-Modal Person Re-Identification with an X Modality

• Diangang Li
• Xing Wei
• Xiaopeng Hong
• Yihong Gong

This paper focuses on the emerging Infrared-Visible crossmodal person re-identification task (IV-ReID), which takes infrared images as input and matches with visible color images. IV-ReID is important yet challenging, as there is a significant gap between the visible and infrared images. To reduce this ‘gap’, we introduce an auxiliary X modality as an assistant and reformulate infrared-visible dual-mode crossmodal learning as an X-Infrared-Visible three-mode learning problem. The X modality restates from RGB channels to a format with which cross-modal learning can be easily performed. With this idea, we propose an X-Infrared- Visible (XIV) ReID cross-modal learning framework. Firstly, the X modality is generated by a lightweight network, which is learnt in a self-supervised manner with the labels inherited from visible images. Secondly, under the XIV framework, cross-modal learning is guided by a carefully designed modality gap constraint, with information exchanged cross the visible, X, and infrared modalities. Extensive experiments are performed on two challenging datasets SYSU-MM01 and RegDB to evaluate the proposed XIV-ReID approach. Experimental results show that our method considerably achieves an absolute gain of over 7% in terms of rank 1 and mAP even compared with the latest state-of-the-art methods.

IJCAI Conference 2007 Conference Paper

• Xing Wei
• Jimeng Sun
• Xuerui Wang

Traditional probabilistic mixture models such as Latent Dirichlet Allocation imply that data records (such as documents) are fully exchangeable. However, data are naturally collected along time, thus obey some order in time. In this paper, we present Dynamic Mixture Models (DMMs) for online pattern discovery in multiple time series. DMMs do not have the noticeable drawback of the SVD-based methods for data streams: negative values in hidden variables are often produced even with all non-negative inputs. We apply DMM models to two real-world datasets, and achieve significantly better results with intuitive interpretation.