arXiv subjects

Zhiqiang Tian

Publications and source records attributed to Zhiqiang Tian.

At least 19 recordsLinked to original sources

arXiv2026

Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation

Event cameras have shown great potential for robust visual perception, yet scaling event representation learning remains challenging due to the scarcity of large-scale annotated event data. Pretrained image models provide scalable semantic supervision, but existing image-to-event methods rely on rigid pixel-wise or token-wise alignment that overlooks modality discrepancies in texture, density, and appearance, potentially causing semantic collapse and limiting transferability. To address this issue, we propose Hyper-RED, a simple, painless, and scalable image-to-event pretraining framework that transfers high-order semantic structures from images to events. Hyper-RED uses hypergraphs to model and align high-order semantic associations among multiple image and event tokens, enabling cross-modal knowledge transfer while accommodating modality-specific differences rather than enforcing rigid one-to-one correspondence. Specifically, given a paired event--image sample, Hyper-RED leverages DINOv3 to extract spatial token representations and constructs image, event, and cross-modal semantic hypergraphs, where each hyperedge connects multiple semantically correlated tokens. We further introduce a hypergraph relational distillation loss that imposes complementary intra- and cross-modal constraints, enabling the event encoder to inherit image-derived semantic organization while preserving local relational consistency and event-specific characteristics. Experiments on three tasks across five event datasets demonstrate consistent scaling from ViT-S to ViT-L and state-of-the-art performance (Fig.1). The code is available at: https://github.com/meisenwang/Hyper--RED.

cs.CV↗

arXiv2026

Rethinking Event-Based Object Detection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning

Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection (EOD) methods face limitations at both the representation and model levels: prior event representations usually encode temporal information indirectly through redundant structures, while detection models struggle to explicitly aggregate fragmented event responses into coherent high-order object features. To address these limitations, we present \textbf{Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD)}, a unified EOD framework that integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning. Specifically, we introduce \textbf{Hierarchical Temporal Aggregation (HTA)}, a compact three-channel pseudo-RGB representation that explicitly embeds temporal information across intra- and inter-window events. To further enhance detection under sparse and fragmented event responses, we propose \textbf{Frequency-aware Hypergraph Temporal Fusion (FHTF)}, which refines multi-scale event features through temporal evolution modeling and high-order relational reasoning. Extensive experiments on Gen1 (\textbf{+0.8 mAP}), 1Mpx/Gen4 (\textbf{+0.5 mAP}), and eTraM (\textbf{+3.0 mAP}) demonstrate that Ev-DTAD achieves a competitive accuracy--efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning (Fig.~\ref{fig:bubble}). The code is available at: https://github.com/meisenwang/Ev-DTAD.

cs.CV↗

arXiv2026

Revisiting Weight Regularization for Low-Rank Continual Learning

Continual Learning (CL) with large-scale pre-trained models (PTMs) has recently gained wide attention, shifting the focus from training from scratch to continually adapting PTMs. This has given rise to a promising paradigm: parameter-efficient continual learning (PECL), where task interference is typically mitigated by assigning a task-specific module during training, such as low-rank adapters. However, weight regularization techniques, such as Elastic Weight Consolidation (EWC)-a key strategy in CL-remain underexplored in this new paradigm. In this paper, we revisit weight regularization in low-rank CL as a new perspective for mitigating task interference in PECL. Unlike existing low-rank CL methods, we mitigate task interference by regularizing a shared low-rank update through EWC, thereby keeping the storage requirement and inference costs constant regardless of the number of tasks. Our proposed method EWC-LoRA leverages a low-rank representation to estimate parameter importance over the full-dimensional space. This design offers a practical, computational- and memory-efficient solution for CL with PTMs, and provides insights that may inform the broader application of regularization techniques within PECL. Extensive experiments on various benchmarks demonstrate the effectiveness of EWC-LoRA, achieving a stability-plasticity trade-off superior to existing low-rank CL approaches. These results indicate that, even under low-rank parameterizations, weight regularization remains an effective mechanism for mitigating task interference. Code is available at: https://github.com/yaoyz96/low-rank-cl.

cs.LG↗

arXiv2026

IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memory

Retrieval-augmented generation (RAG) equips large language models (LLMs) with reliable knowledge memory. To strengthen cross-text associations, recent research integrates graphs and hypergraphs into RAG to capture pairwise and multi-entity relations as structured links. However, their misaligned memory organization necessitates costly, disjointed retrieval. To address these limitations, we propose IGMiRAG, a framework inspired by human intuition-guided reasoning. It constructs a hierarchical heterogeneous hypergraph to align multi-granular knowledge, incorporating deductive pathways to simulate realistic memory structures. During querying, IGMiRAG distills intuitive strategies via a question parser to control mining depth and memory window, and activates instantaneous memories as anchors using dual-focus retrieval. Mirroring human intuition, the framework guides retrieval resource allocation dynamically. Furthermore, we design a bidirectional diffusion algorithm that navigates deductive paths to mine in-depth memories, emulating human reasoning processes. Extensive evaluations indicate IGMiRAG outperforms the state-of-the-art baseline by 4.8% EM and 5.0% F1 overall, with token costs adapting to task complexity (average 6.3k+, minimum 3.0k+). This work presents a cost-effective RAG paradigm that improves both efficiency and effectiveness.

cs.IR↗

arXiv2025

HIDFlowNet: A Flow-Based Deep Network for Hyperspectral Image Denoising

Hyperspectral image (HSI) denoising is essentially ill-posed since a noisy HSI can be degraded from multiple clean HSIs. However, existing deep learning (DL)-based approaches only restore one clean HSI from the given noisy HSI with a deterministic mapping, thus ignoring the ill-posed issue and always resulting in an over-smoothing problem. Additionally, these DL-based methods often neglect that noise is part of the high-frequency component and their network architectures fail to decouple the learning of low-frequency and high-frequency. To alleviate these issues, this paper proposes a flow-based HSI denoising network (HIDFlowNet) to directly learn the conditional distribution of the clean HSI given the noisy HSI and thus diverse clean HSIs can be sampled from the conditional distribution. Overall, our HIDFlowNet is induced from the generative flow model and is comprised of an invertible decoder and a conditional encoder, which can explicitly decouple the learning of low-frequency and high-frequency information of HSI. Specifically, the invertible decoder is built by staking a succession of invertible conditional blocks (ICBs) to capture the local high-frequency details. The conditional encoder utilizes down-sampling operations to obtain low-resolution images and uses transformers to capture correlations over a long distance so that global low-frequency information can be effectively extracted. Extensive experiments on simulated and real HSI datasets verify that our proposed HIDFlowNet can obtain better or comparable results compared with other state-of-the-art methods.

cs.CV↗

arXiv2025

MMRAG-RFT: Two-stage Reinforcement Fine-tuning for Explainable Multi-modal Retrieval-augmented Generation

Multi-modal Retrieval-Augmented Generation (MMRAG) enables highly credible generation by integrating external multi-modal knowledge, thus demonstrating impressive performance in complex multi-modal scenarios. However, existing MMRAG methods fail to clarify the reasoning logic behind retrieval and response generation, which limits the explainability of the results. To address this gap, we propose to introduce reinforcement learning into multi-modal retrieval-augmented generation, enhancing the reasoning capabilities of multi-modal large language models through a two-stage reinforcement fine-tuning framework to achieve explainable multi-modal retrieval-augmented generation. Specifically, in the first stage, rule-based reinforcement fine-tuning is employed to perform coarse-grained point-wise ranking of multi-modal documents, effectively filtering out those that are significantly irrelevant. In the second stage, reasoning-based reinforcement fine-tuning is utilized to jointly optimize fine-grained list-wise ranking and answer generation, guiding multi-modal large language models to output explainable reasoning logic in the MMRAG process. Our method achieves state-of-the-art results on WebQA and MultimodalQA, two benchmark datasets for multi-modal retrieval-augmented generation, and its effectiveness is validated through comprehensive ablation experiments.

cs.AI↗

arXiv2025

Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enhances the response quality and domain-specific performance of large language models (LLMs) by incorporating external knowledge to combat hallucinations. In recent research, graph structures have been integrated into RAG to enhance the capture of semantic relations between entities. However, it primarily focuses on low-order pairwise entity relations, limiting the high-order associations among multiple entities. Hypergraph-enhanced approaches address this limitation by modeling multi-entity interactions via hyperedges, but they are typically constrained to inter-chunk entity-level representations, overlooking the global thematic organization and alignment across chunks. Drawing inspiration from the top-down cognitive process of human reasoning, we propose a theme-aligned dual-hypergraph RAG framework (Cog-RAG) that uses a theme hypergraph to capture inter-chunk thematic structure and an entity hypergraph to model high-order semantic relations. Furthermore, we design a cognitive-inspired two-stage retrieval strategy that first activates query-relevant thematic content from the theme hypergraph, and then guides fine-grained recall and diffusion in the entity hypergraph, achieving semantic alignment and consistent generation from global themes to local details. Our extensive experiments demonstrate that Cog-RAG significantly outperforms existing state-of-the-art baseline approaches.

cs.IR↗

arXiv2025

Skeleton-based Robust Registration Framework for Corrupted 3D Point Clouds

Point cloud registration is fundamental in 3D vision applications, including autonomous driving, robotics, and medical imaging, where precise alignment of multiple point clouds is essential for accurate environment reconstruction. However, real-world point clouds are often affected by sensor limitations, environmental noise, and preprocessing errors, making registration challenging due to density distortions, noise contamination, and geometric deformations. Existing registration methods rely on direct point matching or surface feature extraction, which are highly susceptible to these corruptions and lead to reduced alignment accuracy. To address these challenges, a skeleton-based robust registration framework is presented, which introduces a corruption-resilient skeletal representation to improve registration robustness and accuracy. The framework integrates skeletal structures into the registration process and combines the transformations obtained from both the corrupted point cloud alignment and its skeleton alignment to achieve optimal registration. In addition, a distribution distance loss function is designed to enforce the consistency between the source and target skeletons, which significantly improves the registration performance. This framework ensures that the alignment considers both the original local geometric features and the global stability of the skeleton structure, resulting in robust and accurate registration results. Experimental evaluations on diverse corrupted datasets demonstrate that SRRF consistently outperforms state-of-the-art registration methods across various corruption scenarios, including density distortions, noise contamination, and geometric deformations. The results confirm the robustness of SRRF in handling corrupted point clouds, making it a potential approach for 3D perception tasks in real-world scenarios.

cs.CV↗

arXiv2025

Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context

Partial point cloud registration is essential for autonomous perception and 3D scene understanding, yet it remains challenging owing to structural ambiguity, partial visibility, and noise. We address these issues by proposing Confidence Estimation under Global Context (CEGC), a unified, confidence-driven framework for robust partial 3D registration. CEGC enables accurate alignment in complex scenes by jointly modeling overlap confidence and correspondence reliability within a shared global context. Specifically, the hybrid overlap confidence estimation module integrates semantic descriptors and geometric similarity to detect overlapping regions and suppress outliers early. The context-aware matching strategy smitigates ambiguity by employing global attention to assign soft confidence scores to correspondences, improving robustness. These scores guide a differentiable weighted singular value decomposition solver to compute precise transformations. This tightly coupled pipeline adaptively down-weights uncertain regions and emphasizes contextually reliable matches. Experiments on ModelNet40, ScanObjectNN, and 7Scenes 3D vision datasets demonstrate that CEGC outperforms state-of-the-art methods in accuracy, robustness, and generalization. Overall, CEGC offers an interpretable and scalable solution to partial point cloud registration under challenging conditions.

cs.CV↗

arXiv2025

Desensitizing for Improving Corruption Robustness in Point Cloud Classification through Adversarial Training

Due to scene complexity, sensor inaccuracies, and processing imprecision, point cloud corruption is inevitable. Over-reliance on input features is the root cause of DNN vulnerabilities. It remains unclear whether this issue exists in 3D tasks involving point clouds and whether reducing dependence on these features can enhance the model's robustness to corrupted point clouds. This study attempts to answer these questions. Specifically, we quantified the sensitivity of the DNN to point cloud features using Shapley values and found that models trained using traditional methods exhibited high sensitivity values for certain features. Furthermore, under an equal pruning ratio, prioritizing the pruning of highly sensitive features causes more severe damage to model performance than random pruning. We propose `Desensitized Adversarial Training' (DesenAT), generating adversarial samples using feature desensitization and conducting training within a self-distillation framework, which aims to alleviate DNN's over-reliance on point clouds features by smoothing sensitivity. First, data points with high contribution components are eliminated, and spatial transformation is used to simulate corruption scenes, generate adversarial samples, and conduct adversarial training on the model. Next, to compensate for information loss in adversarial samples, we use the self-distillation method to transfer knowledge from clean samples to adversarial samples, and perform adversarial training in a distillation manner.Extensive experiments on ModelNet-C and PointCloud-C demonstrate show that the propose method can effectively improve the robustness of the model without reducing the performance of clean data sets. This code is publicly available at \href{https://github.com/JerkyT/DesenAT/tree/master}{https://github.com/JerkyT/DesenAT}.

cs.CV↗

arXiv2025

Joint graph entropy knowledge distillation for point cloud classification and robustness against corruptions

Classification tasks in 3D point clouds often assume that class events \replaced{are }{follow }independent and identically distributed (IID), although this assumption destroys the correlation between classes. This \replaced{study }{paper }proposes a classification strategy, \textbf{J}oint \textbf{G}raph \textbf{E}ntropy \textbf{K}nowledge \textbf{D}istillation (JGEKD), suitable for non-independent and identically distributed 3D point cloud data, \replaced{which }{the strategy } achieves knowledge transfer of class correlations through knowledge distillation by constructing a loss function based on joint graph entropy. First\deleted{ly}, we employ joint graphs to capture add{the }hidden relationships between classes\replaced{ and}{,} implement knowledge distillation to train our model by calculating the entropy of add{add }graph.\replaced{ Subsequently}{ Then}, to handle 3D point clouds \deleted{that is }invariant to spatial transformations, we construct \replaced{S}{s}iamese structures and develop two frameworks, self-knowledge distillation and teacher-knowledge distillation, to facilitate information transfer between different transformation forms of the same data. \replaced{In addition}{ Additionally}, we use the above framework to achieve knowledge transfer between point clouds and their corrupted forms, and increase the robustness against corruption of model. Extensive experiments on ScanObject, ModelNet40, ScanntV2\_cls and ModelNet-C demonstrate that the proposed strategy can achieve competitive results.

cs.CV↗

arXiv2025

ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement

Low-light image enhancement aims to restore the under-exposure image captured in dark scenarios. Under such scenarios, traditional frame-based cameras may fail to capture the structure and color information due to the exposure time limitation. Event cameras are bio-inspired vision sensors that respond to pixel-wise brightness changes asynchronously. Event cameras' high dynamic range is pivotal for visual perception in extreme low-light scenarios, surpassing traditional cameras and enabling applications in challenging dark environments. In this paper, inspired by the success of the retinex theory for traditional frame-based low-light image restoration, we introduce the first methods that combine the retinex theory with event cameras and propose a novel retinex-based low-light image restoration framework named ERetinex. Among our contributions, the first is developing a new approach that leverages the high temporal resolution data from event cameras with traditional image information to estimate scene illumination accurately. This method outperforms traditional image-only techniques, especially in low-light environments, by providing more precise lighting information. Additionally, we propose an effective fusion strategy that combines the high dynamic range data from event cameras with the color information of traditional images to enhance image quality. Through this fusion, we can generate clearer and more detail-rich images, maintaining the integrity of visual information even under extreme lighting conditions. The experimental results indicate that our proposed method outperforms state-of-the-art (SOTA) methods, achieving a gain of 1.0613 dB in PSNR while reducing FLOPS by \textbf{84.28}\%.

cs.CV↗

arXiv2025

Combining intrinsic and sliding-induced polarizations for multistates in two dimensional ferroelectrics

Going beyond the bistability paradigm of the charge polarizations in ferroelectrics is highly desired for ferroelectric (FE) memory devices toward ultra-high-density information storage. Here, we propose to build multistates by combining the intrinsic and sliding-induced polarizations. The physics is that there is at least one order of magnitude difference in the energy barriers between these two types of polarization, which leads to a significant difference in the electric fields for reversing the polarization. This difference, along with the symmetry breaking, allows for a unique flipping mechanism involving layer-by-layer sliding followed by layer-by-layer flipping during the transformation of the multistates. As a result, six and ten switchable states can be achieved for the 1T" bilayers and trilayers, respectively. We further illustrate the concept in H-stacking bilayers and trilayers of 1T" transition-metal dichalcogenides by first-principles calculations. Our study provides a new route to design novel polarization states for developing next-generation memory devices.

cond-mat.mtrl-sci↗

arXiv2024

SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field

Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems. Recently, object-free methods have attracted considerable attention. Such methods perceive the world by predicting the semantics of discrete voxel grids but fail to construct continuous and accurate obstacle surfaces. To this end, in this paper, we propose SurroundSDF to implicitly predict the signed distance field (SDF) and semantic field for the continuous perception from surround images. Specifically, we introduce a query-based approach and utilize SDF constrained by the Eikonal formulation to accurately describe the surfaces of obstacles. Furthermore, considering the absence of precise SDF ground truth, we propose a novel weakly supervised paradigm for SDF, referred to as the Sandwich Eikonal formulation, which emphasizes applying correct and dense constraints on both sides of the surface, thereby enhancing the perceptual accuracy of the surface. Experiments suggest that our method achieves SOTA for both occupancy prediction and 3D scene reconstruction tasks on the nuScenes dataset.

cs.CV↗

arXiv2024

Ferroelectrically tunable topological phase transition in In$_2$Se$_3$ thin films

Materials with ferroelectrically switchable topological properties are of interest for both fundamental physics and practical applications. Using first-principles calculations, we find that stacking ferroelectric $α$-In$_2$Se$_3$ monolayers into a bilayer leads to polarization-dependent band structures, which yields polarization-dependent topological properties. Specifically, we find that the states with interlayer ferroelectric couplings are quantum spin Hall insulators, while those with antiferroelectric polarizations are normal insulators. We further find that In$_2$Se$_3$ trilayer and quadlayer exhibit nontrivial band topology as long as in the structure the ferroelectric In$_2$Se$_3$ bilayer is antiferroelectrically coupled to In$_2$Se$_3$ monolayers or other ferroelectric In$_2$Se$_3$ bilayer. Otherwise the system is topologically trivial. The reason is that near the Fermi level the band structure of the ferroelectric In$_2$Se$_3$ bilayer has to be maintained for the nontrivial band topology. This feature can be used to design nontrivial band topology for the thicker films by a proper combination of the interlayer polarization couplings. The topological properties can be ferroelectrically tunable using the dipole locking effect. Our study reveals switchable band topology in a family of natural ferroelectrics, which provide a platform for designing new functional devices.

cond-mat.mtrl-sci↗

arXiv2024

Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models

Federated learning encounters substantial challenges with heterogeneous data, leading to performance degradation and convergence issues. While considerable progress has been achieved in mitigating such an impact, the reliability aspect of federated models has been largely disregarded. In this study, we conduct extensive experiments to investigate the reliability of both generic and personalized federated models. Our exploration uncovers a significant finding: \textbf{federated models exhibit unreliability when faced with heterogeneous data}, demonstrating poor calibration on in-distribution test data and low uncertainty levels on out-of-distribution data. This unreliability is primarily attributed to the presence of biased projection heads, which introduce miscalibration into the federated models. Inspired by this observation, we propose the "Assembled Projection Heads" (APH) method for enhancing the reliability of federated models. By treating the existing projection head parameters as priors, APH randomly samples multiple initialized parameters of projection heads from the prior and further performs targeted fine-tuning on locally available data under varying learning rates. Such a head ensemble introduces parameter diversity into the deterministic model, eliminating the bias and producing reliable predictions via head averaging. We evaluate the effectiveness of the proposed APH method across three prominent federated benchmarks. Experimental results validate the efficacy of APH in model calibration and uncertainty estimation. Notably, APH can be seamlessly integrated into various federated approaches but only requires less than 30\% additional computation cost for 100$\times$ inferences within large models.

cs.LG↗

arXiv2024

Doping induced multiferroicity and quantum anomalous Hall effect in $α$-In$_2$Se$_3$ thin films

In flat-band materials, the strong Coulomb interaction between electrons can lead to exotic physical phenomena. Recently, $α$-In$_2$Se$_3$ thin films were found to possess ferroelectricity and flat bands. In this work, using first-principles calculations, we find that for the monolayer, there is a Weyl point at $Γ$ in the flat band, where the inclusion of the spin-orbit coupling opens a gap. Shifting the Fermi level into the spin-orbit gap gives rise to nontrivial band topology, which is preserved for the bilayer regardless of the interlayer polarization couplings. We further calculate the Chern number and edge states for both the monolayer and bilayer, for which the results suggest that they become quantum anomalous Hall insulators under appropriate dopings. Moreover, we find that the doping-induced magnetism for In$_2$Se$_3$ bilayer is strongly dependent on the interlayer polarization coupling. Therefore, doping the flat bands in In$_2$Se$_3$ bilayer can also yield multiferroicity, where the magnetism is electrically tunable as the system transforms between different polarization states. Our study thus reveals that multiferroicity and nontrivial band topology can be unified into one material for designing multifunctional electronic devices.

cond-mat.mtrl-sci↗

arXiv2023

Ferroelectrically switchable magnetic multistates in MnBi$_2$Te$_4$(Bi$_2$Te$_3$)$_n$ and MnSb$_2$Te$_4$(Sb$_2$Te$_3$)$_n$ (n = 0, 1) thin films

Ferroelectric control of two-dimensional magnetism is promising in fabricating electronic devices with high speed and low energy consumption. The newly discovered layered MnBi$_2$Te$_4$(Bi$_2$Te$_3$)$_n$ and their Sb counterparts exhibit A-type antiferromagnetism with intriguing topological properties. Here, we propose to obtain tunable magnetic multistates in their thin films by ferroelectrically manipulating the interlayer magnetic couplings (IMCs) based on the Heisenberg model and first-principles calculations. Our strategy relies on that interfacing the thin films with appropriate ferroelectric materials can switch on/off an interlayer hopping channel between Mn-$e_g$ orbitals as the polarizations reversed, thus resulting in a switchable interlayer antiferromagnetism-to-ferromagnetism transition. On the other hand, the interface effect leads to asymmetric energy barrier heights for the two polarization states. These properties allow us to build ferroelectrically switchable triple and quadruple magnetic states with multiple Chern numbers in thin films. Our study reveals that ferroelectrically switchable magnetic and topological multistates in MnBi$_2$Te$_4$ family can be obtained by rational design for multifunctional electronic devices, which can also be applied to other two-dimensional magnetic materials.

cond-mat.mtrl-sci↗