Author name cluster

Luping Ji

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.

13 papers

2 author rows

AAAI Conference 2026 Conference Paper

Cross-domain Joint Learning with Prototype-guided Mixture-of-Experts for Infrared Moving Small Target Detection

Weiwei Duan
Luping Ji
Jianghong Huang
Sicheng Zhu
Mao Ye

Infrared small target detection often faces significant domain gaps across datasets due to varying sensors and scene distributions. Currently, most existing methods are typically based on single-domain learning (i.e., training and test are on the same dataset), requiring training separate detectors when considering different datasets. However, they overlook the valuable public knowledge across domains and limit the applicability in multiple infrared scenarios. To break through single-domain learning, implementing only one universal detector simultaneously on multiple datasets, as the first exploration, we propose a cross-domain joint learning task framework with prototype-guided Mixture-of-Experts (CoMoE). Specifically, it designs a hyperspherical prototype learning to adaptively maintain both domain-specific prototypes and global prototypes, enhancing cross-domain feature representation. Meanwhile, a domain-aware Mixture-of-Experts with Top-K routing strategy is proposed to select the optimal domain experts. Moreover, to enhance cross-domain feature alignment, we design an adaptive cross-domain feature modulation with noise-guided contrastive learning. The extensive experiments on a newly constructed benchmark comprising three datasets verify the superiority of our CoMoE, even under limited data settings. It could often surpass general joint learning methods, and state-of-the-art (SOTA) single-domain ones.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Domain-Auxiliary Infrared Moving Small Target Detection by Learning to Overlook Domain Discrepancy

Shengjia Chen
Luping Ji
Shuang Peng
Sicheng Zhu
Mao Ye

Currently, almost all traditional infrared small target detection methods work on the assumption that training and test sets always belong to the same domain, and training samples are sufficient. However, in real applications, a new detection task could often have no sufficient training samples from a special domain. In this situation, adopting the auxiliary data from big-sample domains is usually believed to be one of the most potential solutions. However, exceeding expectations, it is found that simply adding auxiliary samples cannot often be always effective, even causing performance decline, due to existing infrared domain shift. To overcome this unexpected problem, we propose the first infrared moving small target detection framework with domain-auxiliary supports by Learning to Overlook Domain Discrepancy (Loddis). This framework consists of three primary processing stages: correlation weakening, domain confusing, and target consistency contrastive learning. Breaking through traditional learning paradigm, through auxiliary data, it enables the model to focus more on targets themselves, and less on image backgrounds, minimizing the sensitivity to domain discrepancy. The extensive experiments on 6 different-domain datasets show the effectiveness and superiority of the proposed Loddis framework for infrared small target detection.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Multi-view Invariance Learning for 3D Scene Graph Pre-training via Collaborative Cross-Modal Regularization

Yucheng Huang
Luping Ji
Ruijie Xiao
Jiayuan Sun

3D scene graph generation is a pivotal task in scene understanding. Its performance is easy to be constrained by the limited availability of annotated data. Currently, the existing solutions on point cloud pre-training usually emphasize on object-centric representations while neglecting the predicate feature learning. This limitation significantly hinders their relational reasoning capabilities, as inter-object relationships are fundamentally governed by predicate features. To enhance 3D Scene Graphs Pre-training, this paper proposes a task-specific Multi-view Invariance Learning framework with Collaborative Cross-modal Regularization. In detail, the inherent horizontal-rotation invariance of 3D objects and their semantic relationships are leveraged to construct a self-supervised paradigm for triplet feature learning. Moreover, our framework harnesses the cross-modal prior knowledge from the vision-language model to regularize model optimization. It could further achieve the semantic discrimination via unsupervised deep clustering. To resolve the knowledge discrepancies arising from the pre-trained model in fine-tuning, a predicate adapter equipped with knowledge filtering gate is devised to selectively aggregate the predicate features of pre-trained model. Extensive experiments demonstrate that our framework is effective in boosting 3D scene graph generation performance, surpassing state-of-the-art ones.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SeViL: Semi-supervised Vision-Language Learning with Text Prompt Guiding for Moving Infrared Small Target Detection

Weiwei Duan
Luping Ji
Jianghong Huang
Sicheng Zhu

Unlike traditional object detection, moving infrared small target detection is highly challenging due to tiny target size and limited labeled samples. Currently, most existing methods mainly focus on the pure-vision features usually by fully-supervised learning, heavily relying on extensive high-cost manual annotations. Moreover, they almost have not concerned the potentials of multi-modal (e.g., vision and text) learning yet. To address these issues, inspired by prevalent vision-language models, we propose the first semi-supervised vision-language (SeViL) framework with adaptive text prompt guiding. Breaking through traditional pure-vision modality, it takes text prompts as prior knowledge to adaptively enhance target regions and then filter the low-quality pseudo-labels generated on unlabeled data. In the meanwhile, we employ an adaptive cross-modal masking strategy to align text and vision features, promoting cross-modal deep interactions. Remarkably, our extensive experiments on three public datasets (DAUB, ITSDT-15K and IRDST) verify that our new scheme could outperform other semi-supervised ones, and even achieve comparable performance to fully-supervised state-of-the-art (SOTA) methods, with only 10% labeled training samples.

PDF Details DOI

EAAI Journal 2025 Journal Article

Adaptive graph attention networks with interactive learning for attributed graph clustering

Weiwei Duan
Luping Ji
Lijun Wu
Qi Deng
Zhiyuan Li

Attributed graph clustering aims to classify nodes into distinct clusters by learning graph embeddings from both graph structures and node attributes. Recently, methods based on graph neural networks have demonstrated their effectiveness through a two-stage process, i. e. , first obtaining graph embeddings and then performing clustering. However, due to the independence of each stage, the graph embeddings obtained by these methods are not specifically designed for attributed graph clustering. To address this issue, we propose a new artificial intelligence scheme, the Adaptive Graph Attention Networks with Interactive Learning (AGAT-IL). In our scheme, it effectively integrates graph feature learning with clustering in an interactive framework. In detail, we design Laplacian Smoothing Filters to alleviate the high-frequency disturbances in node attributes. Then, an Adaptive Graph Attention Encoder with modularity maximization is proposed to obtain high-quality graph embeddings tailored for clustering. Furthermore, we design an Interactive Learning Unit based on the Kullback–Leibler divergence to further optimize graph embeddings according to the clustering results. To our best knowledge, the proposed AGAT-IL is the first work to enhance graph feature learning through interactive learning. The extensive experiments on four benchmark datasets show the superiority of our AGAT-IL over state-of-the-art methods, almost 3% higher than the best F1 on each dataset. Our codes are available at https: //github. com/MrDec/AGAT-IL.

Details DOI

ICLR Conference 2025 Conference Paper

Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology

Pei Liu 0008
Luping Ji
Jiaxiang Gou
Bo Fu 0007
Mao Ye 0001

Histopathology Whole-Slide Images (WSIs) provide an important tool to assess cancer prognosis in computational pathology (CPATH). While existing survival analysis (SA) approaches have made exciting progress, they are generally limited to adopting highly-expressive network architectures and only coarse-grained patient-level labels to learn visual prognostic representations from gigapixel WSIs. Such learning paradigm suffers from critical performance bottlenecks, when facing present scarce training data and standard multi-instance learning (MIL) framework in CPATH. To overcome it, this paper, for the first time, proposes a new Vision-Language-based SA (**VLSA**) paradigm. Concretely, (1) VLSA is driven by pathology VL foundation models. It no longer relies on high-capability networks and shows the advantage of *data efficiency*. (2) In vision-end, VLSA encodes textual prognostic prior and then employs it as *auxiliary signals* to guide the aggregating of visual prognostic features at instance level, thereby compensating for the weak supervision in MIL. Moreover, given the characteristics of SA, we propose i) *ordinal survival prompt learning* to transform continuous survival labels into textual prompts; and ii) *ordinal incidence function* as prediction target to make SA compatible with VL-based prediction. Notably, VLSA's predictions can be interpreted intuitively by our Shapley values-based method. The extensive experiments on five datasets confirm the effectiveness of our scheme. Our VLSA could pave a new way for SA in CPATH by offering weakly-supervised MIL an effective means to learn valuable prognostic clues from gigapixel WSIs. Our source code is available at https://github.com/liupei101/VLSA.

Details

AAAI Conference 2025 Conference Paper

Mining In-distribution Attributes in Outliers for Out-of-distribution Detection

Yutian Lei
Luping Ji
Pei Liu

Out-of-distribution (OOD) detection is indispensable for deploying reliable machine learning systems in real-world scenarios. Recent works, using auxiliary outliers in training, have shown good potential. However, they seldom concern the intrinsic correlations between in-distribution (ID) and OOD data. In this work, we discover an obvious correlation that OOD data usually possesses significant ID attributes. These attributes should be factored into the training process, rather than blindly suppressed as in previous approaches. Based on this insight, we propose a structured multi-view-based out-of-distribution detection learning (MVOL) framework, which facilitates rational handling of the intrinsic in-distribution attributes in outliers. We provide theoretical insights on the effectiveness of MVOL for OOD detection. Extensive experiments demonstrate the superiority of our framework to others. MVOL effectively utilizes both auxiliary OOD datasets and even wild datasets with noisy ID data.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Motion Prior Knowledge Learning with Homogeneous Language Descriptions for Moving Infrared Small Target Detection

Shengjia Chen
Luping Ji
Weiwei Duan
Shuang Peng
Mao Ye

Different from traditional object detection, pure vision is not enough to infrared small target detection, due to small target size and weak background contrast. For promoting detection performance, more target representations are needed. Currently, motion representations have been proved to be one of the most potential feature kinds for infrared small target detection. Existing methods have an obvious weakness, that besides vision features, they could only capture coarse motion representations from temporal domain. With vision features, fine motion representations could be more effective to enhance detection performance. To overcome this weakness, inspired by prevalent vision-language models, we propose the first vision-language framework with motion prior knowledge learning (MoPKL). Breaking through traditional pure-vision modality, it utilizes homogeneous language descriptions, formatted for moving targets, to directionally guide vision channel learning motion prior knowledge. With the facilitation of motion-vision alignment and motion-relation mining, the motion of infrared small targets is further refined by graph attention, to generate more fine motion representations. The extensive experiments on datasets ITSDT-15K and IRDST show that our framework is effective. It could often obviously outperform other methods.

PDF Details DOI

EAAI Journal 2025 Journal Article

Moving infrared dim and small target detection by mixed spatio-temporal encoding

Shuang Peng
Luping Ji
Shengjia Chen
Weiwei Duan
Sicheng Zhu

Infrared dim and small target detection has become a challenging and hot topic in recent years. Due to the extremely small pixels and low intensity of targets, the existing methods based on single frame seldom consider the temporal relationship between frames, thus often resulting in poor detection performance. Moreover, unlike general objects, the detection task suffers from an overwhelming amount of background information. Usually, directly employing inter-frame attention mechanisms or Convolutional Long Short Term Memory would introduce excessive interfering information and computational load. To advance the detection of infrared dim and small targets and enhance the application of artificial intelligence techniques in this field, this paper explores an artificial intelligence-based method for spatio-temporal feature fusion, which is prevalent in the video domain. Simply but effectively, we propose an infrared target detection network based on spatio-temporal feature fusion principles. It consists of two parallel feature extraction branches. One is designed to extract temporal features across entire video clip, and the other is designed to isolate spatial features from a selected key frame. Following this, a self-refining module comes into play, adaptively adjusting the extracted temporal features and fusing spatio-temporal features at different scales, enhancing deep feature representation. The extensive experiments on two public datasets validate our method simple yet effective. It could reduce floating point operations per second (FLOPs) obviously, promote inference speed, and achieve superior detection accuracy in comparison to current state-of-the-art methods. Our code is publicly accessible at https: //github. com/UESTC-nnLab/STME.

Details DOI

NeurIPS Conference 2025 Conference Paper

Multimodal Causal Reasoning for UAV Object Detection

Nianxin Li
Mao Ye
Lihua Zhou
Shuaifeng Li
Song Tang
Luping Ji
Ce Zhu

Unmanned Aerial Vehicle (UAV) object detection faces significant challenges due to complex environmental conditions and different imaging conditions. These factors introduce significant changes in scale and appearance, particularly for small objects that occupy limited pixels and exhibit limited information, complicating detection tasks. To address these challenges, we propose a Multimodel Causal Reasoning framework based on YOLO backbone for UAV Object Detection (MCR-UOD). The key idea is to use the backdoor adjustment to discover the condition-invariant object representation for easy detection. Specifically, the YOLO backbone is first adjusted to incorporate the pre-trained vision-language model. The original category labels are replaced with semantic text prompts, and the detection head is replaced with text-image contrastive learning. Based on this backbone, our method consists of two parts. The first part, named language guided region exploration, discovers the regions with high probability of object existence using text embeddings based on vision-language model such as CLIP. Another part is the backdoor adjustment casual reasoning module, which constructs a confounder dictionary tailored to different imaging conditions to capture global image semantics and derives a prior probability distribution of shooting conditions. During causal inference, we use the confounder dictionary and the prior to intervene on local instance features, disentangling condition variations, and obtaining condition-invariant representations. Experimental results on several public datasets confirm the state-of-the-art performance of our approach. The code, data and models will be released upon publication of this paper.

PDF Details

AAAI Conference 2025 Conference Paper

Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification

Jiaxiang Gou
Luping Ji
Pei Liu
Mao Ye

Whole Slide Image (WSI) classification has very significant applications in clinical pathology, e.g., tumor identification and cancer diagnosis. Currently, most research attention is focused on Multiple Instance Learning (MIL) using static datasets. One of the most obvious weaknesses of these methods is that they cannot efficiently preserve and utilize previously learned knowledge. With any new data arriving, classification models are required to be re-trained on both previous and current new data. To overcome this shortcoming and break through traditional vision modality, this paper proposes the first Vision-Language-based framework with Queryable Prototype Multiple Instance Learning (QPMIL-VL) specially designed for incremental WSI classification. This framework mainly consists of two information processing branches: one is for generating bag-level features by prototype-guided aggregation of instance features, while the other is for enhancing class features through a combination of class ensemble, tunable vector and class similarity loss. The experiments on four public WSI datasets demonstrate that our QPMIL-VL framework is effective for incremental WSI classification and often significantly outperforms other compared methods, achieving state-of-the-art (SOTA) performance.

PDF Details DOI

EAAI Journal 2024 Journal Article

Spatio-temporal fusion with motion masks for the moving small target detection from remote-sensing videos

Sicheng Zhu
Luping Ji
Jiewen Zhu
Shengjia Chen
Haohao Ren

Moving small target detection is an eye-catching research topic, full of great challenges in object detection field. Its primary difficulties exist in (i) the very small size proportion of the target region in background images, (ii) the quite weak contrast to background and (iii) the perception of slight target motion. Currently-existing detection methods mainly utilize the image features from spatial domain. This kind of features is quite weak to small targets. More new feature kinds need to be concerned. In view of these, besides traditional image clues, motion features are currently attracting more and more attention in small target detection. In order to promote detection performance, this paper proposes a Spatio-Temporal Fusion Network (STFNet) with two parallel feature extraction branches for detecting moving small targets. In this network, one branch is designed to capture the traditional semantic features from spatial domain, and the other is devised to perceive the slight target motion features hidden in temporal domain. Meanwhile, to optimize the extraction of spatio-temporal features, a group of motion masks is specially designed to guide feature extractors to pay more precise attention to the positions where small targets appear. Moreover, we design a new bridging module to enhance the cross-domain and cross-scale fusion of spatio-temporal features. Through extensive comparison and ablation experiments on seven sub-datasets, it is proved that our new STFNet is effective and it is obviously superior to the compared ones in detecting moving small targets from satellite sequence images. It achieves a Precision of 0. 93, an mAP50 of 71. 10% and an F 1 of 0. 84, evidently higher than existing state-of-the-art methods. Our codes are available at https: //github. com/UESTC-nnLab/STF.

Details DOI

ICML Conference 2024 Conference Paper

Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation

Pei Liu 0008
Luping Ji

Uncertainty estimation (UE), as an effective means of quantifying predictive uncertainty, is crucial for safe and reliable decision-making, especially in high-risk scenarios. Existing UE schemes usually assume that there are completely-labeled samples to support fully-supervised learning. In practice, however, many UE tasks often have no sufficiently-labeled data to use, such as the Multiple Instance Learning (MIL) with only weak instance annotations. To bridge this gap, this paper, for the first time, addresses the weakly-supervised issue of Multi-Instance UE (MIUE) and proposes a new baseline scheme, Multi-Instance Residual Evidential Learning (MIREL). Particularly, at the fine-grained instance UE with only weak supervision, we derive a multi-instance residual operator through the Fundamental Theorem of Symmetric Functions. On this operator derivation, we further propose MIREL to jointly model the high-order predictive distribution at bag and instance levels for MIUE. Extensive experiments empirically demonstrate that our MIREL not only could often make existing MIL networks perform better in MIUE, but also could surpass representative UE methods by large margins, especially in instance-level UE tasks. Our source code is available at https: //github. com/liupei101/MIREL.

Details