Author name cluster

Liang Wan

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.

16 papers

1 author row

AAAI Conference 2026 Conference Paper

E-Logic Prompt: Unified Energy-Logic Framework for Continual Visual Question Answering

Jiayao Tan
Tianle Liu
Fuyuan Hu
Wei Feng
Liang Wan

Prompt tuning has shown promise for continual visual question answering (CVQA), facilitating modular and transferable knowledge across tasks. However, existing approaches often overlook the guiding role of prompts in the model’s implicit reasoning process. This oversight can lead to inconsistent reasoning paths and performance degradation across tasks. To address this issue, we propose the E Logic Prompt framework, which employs energy-based models (EBMs) to model the semantic compatibility between prompts and queries. In this framework, prompts function not only as adapters but also as reasoning guides that help maintain coherence throughout the inference process. The framework enforces logical consistency at three levels. At the input level, it selects semantically aligned prompts by minimizing the energy between queries and prompts. Within the model, it aligns intermediate representations with prompts across layers to preserve step-by-step reasoning. Across tasks, it applies energy-based constraints to regulate prompt behavior, effectively suppressing semantic drift and enabling prompt reuse. These three levels of consistency together enhance the guiding capacity of prompts, allowing them to steer the model toward more stable and coherent reasoning. Extensive experiments show that E Logic Prompt outperforms existing methods in both accuracy and knowledge retention, while effectively maintaining balanced cross-modal reasoning throughout continual learning.

PDF Details DOI

JBHI Journal 2025 Journal Article

Completed Feature Disentanglement Learning for Multimodal MRIs Analysis

Tianling Liu
Hongying Liu
Fanhua Shang
Lequan Yu
Tong Han
Liang Wan

Multimodal MRIs play a crucial role in clinical diagnosis and treatment. Feature disentanglement (FD)-based methods, aiming at learning superior feature representations for multimodal data analysis, have achieved significant success in multimodal learning (MML). Typically, existing FD-based methods separate multimodal data into modality-shared and modality-specific features, and employ concatenation or attention mechanisms to integrate these features. However, our preliminary experiments indicate that these methods could lead to a loss of shared information among subsets of modalities when the inputs contain more than two modalities, and such information is critical for prediction accuracy. Furthermore, these methods do not adequately interpret the relationships between the decoupled features at the fusion stage. To address these limitations, we propose a novel Complete Feature Disentanglement (CFD) strategy that recovers the lost information during feature decoupling. Specifically, the CFD strategy not only identifies modality-shared and modality-specific features, but also decouples shared features among subsets of multimodal inputs, termed as modality-partial-shared features. We further introduce a new Dynamic Mixture-of-Experts Fusion (DMF) module that dynamically integrates these decoupled features, by explicitly learning the local-global relationships among the features. The effectiveness of our approach is validated through classification tasks on three multimodal MRI datasets. Extensive experimental results demonstrate that our approach outperforms other state-of-the-art MML methods with obvious margins, showcasing its superior performance.

Details DOI

YNIMG Journal 2025 Journal Article

In vivo cortical microstructure mapping using high-gradient diffusion MRI accounting for intercompartmental water exchange effects

Tanxin Dong
Hong-Hsi Lee
Han Zang
Hansol Lee
Qiyuan Tian
Liang Wan
Qiuyun Fan
SusieY. Huang

In recent years, mapping tissue microstructure in the cortex using high gradient diffusion MRI has received growing attention. The Soma And Neurite Density Imaging (SANDI) explicitly models the soma compartment in the cortex assuming impermeable membranes. As such, it does not account for diffusion time dependence due to water exchange in the estimated microstructural properties, as neurites in gray matter are much less myelinated than in white matter. In this work, we performed a systematic evaluation of an extended SANDI model for in vivo human cortical microstructural mapping that accounts for water exchange effects between the neurite and extracellular compartments using the anisotropic Kärger model. We refer to this model as in vivo SANDIX, adapting the nomenclature from previous publications. As in the original SANDI model, the soma compartment is modeled as an impermeable sphere due to the much smaller surface-to-volume ratio compared to the neurite compartment. A Monte Carlo simulation study was performed to examine the sensitivity of the in vivo SANDIX model to sphere radii, compartment fractions, and water exchange times. The simulation results indicate that the proposed in vivo SANDIX framework can account for the water exchange effect and provide measures of intra-soma and intra-neurite signal fractions without spurious time-dependence in estimated parameters, whereas the measured water exchange times need to be interpreted with caution. The model was then applied to in vivo diffusion MRI data acquired in 13 healthy adults on the 3-Tesla Connectome MRI scanner equipped with 300 mT/m gradients. The in vivo results exhibited patterns that were consistent with corresponding anatomical characteristics in both cortex and white matter. In particular, the estimated water exchange times in gray and white matter were distinct and differentiated between the two tissue types. Our results show the SANDIX approach applied to high-gradient diffusion MRI data achieves cortical microstructure mapping of the in vivo human brain with the evaluation of water exchange effects. This approach potentially provides a more appropriate description of in vivo cortical microstructure for improving data interpretation in future neurobiological studies.

Details DOI

NeurIPS Conference 2025 Conference Paper

QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution

Zhenwei Zhang
Fanhua Shang
Hongying Liu
Liang Wan
Wei Feng
Yanming Hui

While model quantization has become pivotal for deploying super-resolution (SR) networks on mobile devices, existing works focus on quantization methods only for image super-resolution. Different from image SR quantization, the temporal error propagation, shared temporal parameterization, and temporal metric mismatch significantly degrade the quantization performance of a video SR model. To address these issues, we propose the first quantization method, QBasicVSR, for video super-resolution. A novel temporal awareness adaptation post-training quantization (PTQ) framework for video super-resolution with the flow-gradient video bit adaptation and temporal shared layer bit adaptation is presented. Moreover, we put forward a novel fine-tuning method for VSR with the supervision of the full-precision model. Our method achieves extraordinary performance with state-of-the-art efficient VSR approaches, delivering up to $\times$200 faster processing speed while utilizing only 1/8 of the GPU resources. Additionally, extensive experiments demonstrate that the proposed method significantly outperforms existing PTQ algorithms on various datasets. For instance, it attains a 2. 53 dB increase on the UDM10 benchmark when quantizing BasicVSR to 4-bit with 100 unlabeled video clips. The code and models will be released on GitHub.

PDF Details

AAAI Conference 2025 Conference Paper

Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution

Sen Chen
Hongying Liu
Chaowei Fang
Fanhua Shang
Yuanyuan Liu
Liang Wan
Dongmei Jiang
Yaowei Wang

Blind image super-resolution (blind SR) aims to restore a high-resolution (HR) image from a low-resolution (LR) image with unknown degradation. Many existing methods explicitly estimate degradation information from various LR images. However, in most cases, image degradations are independent of image content. Their estimations may be influenced by the image content resulting in inaccuracy. Unlike existing works, we design a dual-encoder for degradation representation (DEDR) to preclude the influence of image content from LR images. This benefits in extracting the intrinsic degradation representation more accurately. To the best of our knowledge, this paper is the first work that estimates degradation representation through filtering out image content. Based on the degradation representation extracted by DEDR, we present a novel framework, named degradation representation aware transform network (DRAT) for blind SR. We propose global degradation aware (GDA) blocks to propagate degradation information across spatial and channel dimensions, in which a degradation representation transform module (DRT) is introduced to render features degradation-aware, thereby enhancing the restoration of LR images. Extensive experiments are conducted on three benchmark datasets (including Gaussian 8, DIV2KRK, and real-world datasets) under large scaling factors with complex degradations. The experimental results demonstrate that DRAT surpasses state-of-the-art supervised kernel estimation and unsupervised degradation representation methods.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Deep Correlated Prompting for Visual Recognition with Missing Modalities

Lianyu Hu
Tongkai Shi
Wei Feng
Fanhua Shang
Liang Wan

Large-scale multimodal models have shown excellent performance over a series of tasks powered by the large corpus of paired multimodal training data. Generally, they are always assumed to receive modality-complete inputs. However, this simple assumption may not always hold in the real world due to privacy constraints or collection difficulty, where models pretrained on modality-complete data easily demonstrate degraded performance on missing-modality cases. To handle this issue, we refer to prompt learning to adapt large pretrained multimodal models to handle missing-modality scenarios by regarding different missing cases as different types of input. Instead of only prepending independent prompts to the intermediate layers, we present to leverage the correlations between prompts and input features and excavate the relationships between different layers of prompts to carefully design the instructions. We also incorporate the complementary semantics of different modalities to guide the prompting design for each modality. Extensive experiments on three commonly-used datasets consistently demonstrate the superiority of our method compared to the previous approaches upon different missing scenarios. Plentiful ablations are further given to show the generalizability and reliability of our method upon different modality-missing ratios and types.

PDF Details DOI

JBHI Journal 2024 Journal Article

Hybrid Masked Image Modeling for 3D Medical Image Segmentation

Zhaohu Xing
Lei Zhu
Lequan Yu
Zhiheng Xing
Liang Wan

Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the missing pixels, which only considers semantic information at a lower level, and causes a long pre-training time. This paper presents HybridMIM, a novel hybrid self-supervised learning method based on masked image modeling for 3D medical image segmentation. Specifically, we design a two-level masking hierarchy to specify which and how patches in sub-volumes are masked, effectively providing the constraints of higher level semantic information. Then we learn the semantic information of medical images at three levels, including: 1) partial region prediction to reconstruct key contents of the 3D image, which largely reduces the pre-training time burden (pixel-level); 2) patch-masking perception to learn the spatial relationship between the patches in each sub-volume (region-level); and 3) drop-out-based contrastive learning between samples within a mini-batch, which further improves the generalization ability of the framework (sample-level). The proposed framework is versatile to support both CNN and transformer as encoder backbones, and also enables to pre-train decoders for image segmentation. We conduct comprehensive experiments on five widely-used public medical image segmentation datasets, including BraTS2020, BTCV, MSD Liver, MSD Spleen, and BraTS2023. The experimental results show the clear superiority of HybridMIM against competing supervised methods, masked pre-training approaches, and other self-supervised methods, in terms of quantitative metrics, speed performance and qualitative observations.

Details DOI

AAAI Conference 2024 Conference Paper

Long-Tailed Learning as Multi-Objective Optimization

Weiqi Li
Fan Lyu
Fanhua Shang
Liang Wan
Wei Feng

Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models biased towards classes with sufficient samples and performing poorly on rare classes. Recent methods propose to rebalance classes but they undertake the seesaw dilemma (what is increasing performance on tail classes may decrease that of head classes, and vice versa). In this paper, we argue that the seesaw dilemma is derived from the gradient imbalance of different classes, in which gradients of inappropriate classes are set to important for updating, thus prone to overcompensation or undercompensation on tail classes. To achieve ideal compensation, we formulate long-tailed recognition as a multi-objective optimization problem, which fairly respects the contributions of head and tail classes simultaneously. For efficiency, we propose a Gradient-Balancing Grouping (GBG) strategy to gather the classes with similar gradient directions, thus approximately making every update under a Pareto descent direction. Our GBG method drives classes with similar gradient directions to form a more representative gradient and provides ideal compensation to the tail classes. Moreover, we conduct extensive experiments on commonly used benchmarks in long-tailed learning and demonstrate the superiority of our method over existing SOTA methods. Our code is released at https://github.com/WickyLee1998/GBG_v1.

PDF Details DOI

AAAI Conference 2024 Conference Paper

SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network

Zekun Li
Hongying Liu
Fanhua Shang
Yuanyuan Liu
Liang Wan
Wei Feng

Deep learning-based video super-resolution (VSR) networks have gained significant performance improvements in recent years. However, existing VSR networks can only support a fixed integer scale super-resolution task, and when we want to perform VSR at multiple scales, we need to train several models. This implementation certainly increases the consumption of computational and storage resources, which limits the application scenarios of VSR techniques. In this paper, we propose a novel Scale-adaptive Arbitrary-scale Video Super-Resolution network (SAVSR), which is the first work focusing on spatial VSR at arbitrary scales including both non-integer and asymmetric scales. We also present an omni-dimensional scale-attention convolution, which dynamically adapts according to the scale of the input to extract inter-frame features with stronger representational power. Moreover, the proposed spatio-temporal adaptive arbitrary-scale upsampling performs VSR tasks using both temporal features and scale information. And we design an iterative bi-directional architecture for implicit feature alignment. Experiments at various scales on the benchmark datasets show that the proposed SAVSR outperforms state-of-the-art (SOTA) methods at non-integer and asymmetric scales. The source code is available at https://github.com/Weepingchestnut/SAVSR.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

Tingliang Feng
Hao Shi
Xueyang Liu
Wei Feng
Liang Wan
Yanlin Zhou
Di Lin

Many methods of semantic image segmentation have borrowed the success of open compound domain adaptation. They minimize the style gap between the images of source and target domains, more easily predicting the accurate pseudo annotations for target domain's images that train segmentation network. The existing methods globally adapt the scene style of the images, whereas the object styles of different categories or instances are adapted improperly. This paper proposes the Object Style Compensation, where we construct the Object-Level Discrepancy Memory with multiple sets of discrepancy features. The discrepancy features in a set capture the style changes of the same category's object instances adapted from target to source domains. We learn the discrepancy features from the images of source and target domains, storing the discrepancy features in memory. With this memory, we select appropriate discrepancy features for compensating the style information of the object instances of various categories, adapting the object styles to a unified style of source domain. Our method enables a more accurate computation of the pseudo annotations for target domain's images, thus yielding state-of-the-art results on different datasets.

PDF Details

JBHI Journal 2023 Journal Article

Uncertainty-Aware Multi-Dimensional Mutual Learning for Brain and Brain Tumor Segmentation

Junting Zhao
Zhaohu Xing
Zhihao Chen
Liang Wan
Tong Han
Huazhu Fu
Lei Zhu

Existing segmentation methods for brain MRI data usually leverage 3D CNNs on 3D volumes or employ 2D CNNs on 2D image slices. We discovered that while volume-based approaches well respect spatial relationships across slices, slice-based methods typically excel at capturing fine local features. Furthermore, there is a wealth of complementary information between their segmentation predictions. Inspired by this observation, we develop an Uncertainty-aware Multi-dimensional Mutual learning framework to learn different dimensional networks simultaneously, each of which provides useful soft labels as supervision to the others, thus effectively improving the generalization ability. Specifically, our framework builds upon a 2D-CNN, a 2. 5D-CNN, and a 3D-CNN, while an uncertainty gating mechanism is leveraged to facilitate the selection of qualified soft labels, so as to ensure the reliability of shared information. The proposed method is a general framework and can be applied to varying backbones. The experimental results on three datasets demonstrate that our method can significantly enhance the performance of the backbone network by notable margins, achieving a Dice metric improvement of 2. 8% on MeniSeg, 1. 4% on IBSR, and 1. 3% on BraTS2020.

Details DOI

EAAI Journal 2022 Journal Article

DSU-Net: Distraction-Sensitive U-Net for 3D lung tumor segmentation

Junting Zhao
Meng Dang
Zhihao Chen
Liang Wan

Automatic segmentation of lung tumors is a crucial and challenging problem. Many existing methods suffer from ambiguity of tissue regions and tumor regions, which occur with similar appearance. To address this problem, we propose a new cascaded two-stage U-net model, Distraction-Sensitive U-Net (DSU-Net), to explicitly take the ambiguous region information (referred as distraction region) into account. Stage-I generates a global segmentation for the whole input CT volume and predicts latent distraction regions, which contain both false negative areas and false positive areas, against the segmentation ground truth. Stage-II embeds the distraction region information into local segmentation for volume patches to further discriminate the tumor regions. To this end, a Distraction Attention Module (DAM) is proposed and applied in each level of U-Net in Stage-II, to improve the discrimination of features. We evaluate our network on a lung cancer dataset from Gross Target Volume segmentation of MICCAI2019 challenge. Experimental results show that the proposed DSU-Net outperforms existing U-like networks.

Details DOI

NeurIPS Conference 2022 Conference Paper

Exploring Example Influence in Continual Learning

Qing Sun
Fan Lyu
Fanhua Shang
Wei Feng
Liang Wan

Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks). Due to the fact that past training data is not available, it is valuable to explore the influence difference on S and P among training examples, which may improve the learning pattern towards better SP. Inspired by Influence Function (IF), we first study example influence via adding perturbation to example weight and computing the influence derivation. To avoid the storage and calculation burden of Hessian inverse in neural networks, we propose a simple yet effective MetaSP algorithm to simulate the two key steps in the computation of IF and obtain the S- and P-aware example influence. Moreover, we propose to fuse two kinds of example influence by solving a dual-objective optimization problem, and obtain a fused influence towards SP Pareto optimality. The fused influence can be used to control the update of model and optimize the storage of rehearsal. Empirical results show that our algorithm significantly outperforms state-of-the-art methods on both task- and class-incremental benchmark CL datasets.

PDF Details

AAAI Conference 2022 Conference Paper

FFNet: Frequency Fusion Network for Semantic Scene Completion

Xuzhi Wang
Di Lin
Liang Wan

Semantic scene completion (SSC) requires the estimation of the 3D geometric occupancies of objects in the scene, along with the object categories. Currently, many methods employ RGB-D images to capture the geometric and semantic information of objects. These methods use simple but popular spatial- and channel-wise operations, which fuse the information of RGB and depth data. Yet, they ignore the large discrepancy of RGB-D data and the uncertainty measurements of depth data. To solve this problem, we propose the Frequency Fusion Network (FFNet), a novel method for boosting semantic scene completion by better utilizing RGB-D data. FFNet explicitly correlates the RGB-D data in the frequency domain, different from the features directly extracted by the convolution operation. Then, the network uses the correlated information to guide the feature learning from the RG- B and depth images, respectively. Moreover, FFNet accounts for the properties of different frequency components of RGB- D features. It has a learnable elliptical mask to decompose the features learned from the RGB and depth images, attending to various frequencies to facilitate the correlation process of RGB-D data. We evaluate FFNet intensively on the public SSC benchmarks, where FFNet surpasses the state-ofthe-art methods. The code package of FFNet is available at https: //github. com/alanWXZ/FFNet.

PDF Details

AAAI Conference 2020 Conference Paper

Complementary-View Multiple Human Tracking

Ruize Han
Wei Feng
Jiewen Zhao
Zicheng Niu
Yujun Zhang
Liang Wan
Song Wang

The global trajectories of targets on ground can be well captured from a top view in a high altitude, e. g. , by a dronemounted camera, while their local detailed appearances can be better recorded from horizontal views, e. g. , by a helmet camera worn by a person. This paper studies a new problem of multiple human tracking from a pair of top- and horizontalview videos taken at the same time. Our goal is to track the humans in both views and identify the same person across the two complementary views frame by frame, which is very challenging due to very large ﬁeld of view difference. In this paper, we model the data similarity in each view using appearance and motion reasoning and across views using appearance and spatial reasoning. Combing them, we formulate the proposed multiple human tracking as a joint optimization problem, which can be solved by constrained integer programming. We collect a new dataset consisting of top- and horizontal-view video pairs for performance evaluation and the experimental results show the effectiveness of the proposed method.

PDF Details

IJCAI Conference 2018 Conference Paper

Active Recurrence of Lighting Condition for Fine-Grained Change Detection

Qian Zhang
Wei Feng
Liang Wan
Fei-Peng Tian
Ping Tan

This paper addresses active lighting recurrence (ALR), a new problem that actively relocalizes a light source to physically reproduce the lighting condition for a same scene from single reference image. ALR is of great importance for fine-grained visual monitoring and change detection, because some phenomena or minute changes can only be clearly observed under particular lighting conditions. Hence, effective ALR should be able to online navigate a light source toward the target pose, which is challenging due to the complexity and diversity of real-world lighting \& imaging processes. We propose to use the simple parallel lighting as an analogy model and based on Lambertian law to compose an instant navigation ball for this purpose. We theoretically prove the feasibility of this ALR strategy for realistic near point light sources and its invariance to the ambiguity of normal \& lighting decomposition. Extensive quantitative experiments and challenging real-world tasks on fine-grained change monitoring of cultural heritages verify the effectiveness of our approach. We also validate its generality to non-Lambertian scenes.

PDF Details