Wenjia Xu

Wenjia Xu, Yongqin Xian, Jiuniu Wang et al.

Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., word embeddings, enable knowledge transfer between classes. However, word embeddings do not always reflect visual similarities and result in inferior zero-shot performance. We propose to discover semantic embeddings containing discriminative visual properties for zero-shot learning, without requiring any human annotation. Our model visually divides a set of images from seen classes into clusters of local image regions according to their visual similarity, and further imposes their class discrimination and semantic relatedness. To associate these clusters with previously unseen classes, we use external knowledge, e.g., word embeddings and propose a novel class relation discovery module. Through quantitative and qualitative evaluation, we demonstrate that our model discovers semantic embeddings that model the visual properties of both seen and unseen classes. Furthermore, we demonstrate on three benchmarks that our visually-grounded semantic embeddings further improve performance over word embeddings across various ZSL models by a large margin.

Wenjia Xu, Yongqin Xian, Jiuniu Wang et al.

Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play an important role, while in the few-shot regime, the effect of attributes is under-explored. To better transfer attribute-based knowledge from seen to unseen classes, we argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks. To this end, we propose a novel representation learning framework that jointly learns discriminative global and local features using only class-level attributes. While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate features. Furthermore, we introduce a zoom-in module that localizes and crops the informative regions to encourage the network to learn informative features explicitly. We show that our locality augmented image representations achieve a new state-of-the-art on challenging benchmarks, i.e. CUB, AWA2, and SUN. As an additional benefit, our model points to the visual evidence of the attributes in an image, confirming the improved attribute localization ability of our image representation. The attribute localization is evaluated quantitatively with ground truth part annotations, qualitatively with visualizations, and through well-designed user studies.

Song Zhang, Wenjia Xu, Zhiwei Wei et al.

Multi-View Stereo~(MVS) is a fundamental problem in geometric computer vision which aims to reconstruct a scene using multi-view images with known camera parameters. However, the mainstream approaches represent the scene with a fixed all-pixel depth range and equal depth interval partition, which will result in inadequate utilization of depth planes and imprecise depth estimation. In this paper, we present a novel multi-stage coarse-to-fine framework to achieve adaptive all-pixel depth range and depth interval. We predict a coarse depth map in the first stage, then an Adaptive Depth Range Prediction module is proposed in the second stage to zoom in the scene by leveraging the reference image and the obtained depth map in the first stage and predict a more accurate all-pixel depth range for the following stages. In the third and fourth stages, we propose an Adaptive Depth Interval Adjustment module to achieve adaptive variable interval partition for pixel-wise depth range. The depth interval distribution in this module is normalized by Z-score, which can allocate dense depth hypothesis planes around the potential ground truth depth value and vice versa to achieve more accurate depth estimation. Extensive experiments on four widely used benchmark datasets~(DTU, TnT, BlendedMVS, ETH 3D) demonstrate that our model achieves state-of-the-art performance and yields competitive generalization ability. Particularly, our method achieves the highest Acc and Overall on the DTU dataset, while attaining the highest Recall and $F_{1}$-score on the Tanks and Temples intermediate and advanced dataset. Moreover, our method also achieves the lowest $e_{1}$ and $e_{3}$ on the BlendedMVS dataset and the highest Acc and $F_{1}$-score on the ETH 3D dataset, surpassing all listed methods.Project website: https://github.com/zs670980918/ARAI-MVSNet

Zaiquan Yang, Yang Liu, Wenjia Xu et al.

Zero-shot learning (ZSL) aims to recognize unseen classes by exploiting semantic descriptions shared between seen classes and unseen classes. Current methods show that it is effective to learn visual-semantic alignment by projecting semantic embeddings into the visual space as class prototypes. However, such a projection function is only concerned with seen classes. When applied to unseen classes, the prototypes often perform suboptimally due to domain shift. In this paper, we propose to learn prototypes via placeholders, termed LPL, to eliminate the domain shift between seen and unseen classes. Specifically, we combine seen classes to hallucinate new classes which play as placeholders of the unseen classes in the visual and semantic space. Placed between seen classes, the placeholders encourage prototypes of seen classes to be highly dispersed. And more space is spared for the insertion of well-separated unseen ones. Empirically, well-separated prototypes help counteract visual-semantic misalignment caused by domain shift. Furthermore, we exploit a novel semantic-oriented fine-tuning to guarantee the semantic reliability of placeholders. Extensive experiments on five benchmark datasets demonstrate the significant performance gain of LPL over the state-of-the-art methods. Code is available at https://github.com/zaiquanyang/LPL.

Jiuniu Wang, Wenjia Xu, Qingzhong Wang et al.

Recent image captioning models are achieving impressive results based on popular metrics, i.e., BLEU, CIDEr, and SPICE. However, focusing on the most popular metrics that only consider the overlap between the generated captions and human annotation could result in using common words and phrases, which lacks distinctiveness, i.e., many similar images have the same caption. In this paper, we aim to improve the distinctiveness of image captions via comparing and reweighting with a set of similar images. First, we propose a distinctiveness metric -- between-set CIDEr (CIDErBtw) to evaluate the distinctiveness of a caption with respect to those of similar images. Our metric reveals that the human annotations of each image in the MSCOCO dataset are not equivalent based on distinctiveness; however, previous works normally treat the human annotations equally during training, which could be a reason for generating less distinctive captions. In contrast, we reweight each ground-truth caption according to its distinctiveness during training. We further integrate a long-tailed weight strategy to highlight the rare words that contain more information, and captions from the similar image set are sampled as negative examples to encourage the generated sentence to be unique. Finally, extensive experiments are conducted, showing that our proposed approach significantly improves both distinctiveness (as measured by CIDErBtw and retrieval metrics) and accuracy (e.g., as measured by CIDEr) for a wide variety of image captioning baselines. These results are further confirmed through a user study.

Yujie Li, Jiuniu Wang, Mugen Peng et al.

Long-horizon Flexible Job-Shop Scheduling~(FJSP) presents a formidable combinatorial challenge due to complex, interdependent decisions spanning extended time horizons. While learning-based Rolling Horizon Optimization~(RHO) has emerged as a promising paradigm to accelerate solving by identifying and fixing invariant operations, its effectiveness is hindered by the structural complexity of FJSP. Existing methods often fail to capture intricate graph-structured dependencies and ignore the asymmetric costs of prediction errors, in which misclassifying critical-path operations is significantly more detrimental than misclassifying non-critical ones. Furthermore, dynamic shifts in predictive confidence during the rolling process make static pruning thresholds inadequate. To address these limitations, we propose Graph-RHO, a novel critical-path-aware graph-based RHO framework. First, we introduce a topology-aware heterogeneous graph network that encodes subproblems as operation-machine graphs with multi-relational edges, leveraging edge-feature-aware message passing to predict operation stability. Second, we incorporate a critical-path-aware mechanism that injects inductive biases during training to distinguish highly sensitive bottleneck operations from robust ones. Third, we devise an adaptive thresholding strategy that dynamically calibrates decision boundaries based on online uncertainty estimation to align model predictions with the solver's search space. Extensive experiments on standard benchmarks demonstrate that \mbox{Graph-RHO} establishes a new state of the art in solution quality and computational efficiency. Remarkably, it exhibits exceptional zero-shot generalization, reducing solve time by over 30\% on large-scale instances (2000 operations) while achieving superior solution quality. Our code is available \href{https://github.com/IntelliSensing/Graph-RHO}{here}.

Youyuan Zhang, Jiuniu Wang, Hao Wu et al.

Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can distinguish the target image from other similar images. To evaluate the distinctiveness of captions, we introduce a series of metrics that use large-scale vision-language pre-training model CLIP to quantify the distinctiveness. To further improve the distinctiveness of captioning models, we propose a simple and effective training strategy that trains the model by comparing target image with similar image group and optimizing the group embedding gap. Extensive experiments are conducted on various baseline models to demonstrate the wide applicability of our strategy and the consistency of metric results with human evaluation. By comparing the performance of our best model with existing state-of-the-art models, we claim that our model achieves new state-of-the-art towards distinctiveness objective.

Haoling Li, Jiuniu Wang, Zhiwei Wei et al.

Navigation and localization of UAVs present a challenge when global navigation satellite systems (GNSS) are disrupted and unreliable. Traditional techniques, such as simultaneous localization and mapping (SLAM) and visual odometry (VO), exhibit certain limitations in furnishing absolute coordinates and mitigating error accumulation. Existing visual localization methods achieve autonomous visual localization without error accumulation by matching with ortho satellite images. However, doing so cannot guarantee real-time performance due to the complex matching process. To address these challenges, we propose a novel Global-Local Visual Localization (GLVL) network. Our GLVL network is a two-stage visual localization approach, combining a large-scale retrieval module that finds similar regions with the UAV flight scene, and a fine-grained matching module that localizes the precise UAV coordinate, enabling real-time and precise localization. The training process is jointly optimized in an end-to-end manner to further enhance the model capability. Experiments on six UAV flight scenes encompassing both texture-rich and texture-sparse regions demonstrate the ability of our model to achieve the real-time precise localization requirements of UAVs. Particularly, our method achieves a localization error of only 2.39 meters in 0.48 seconds in a village scene with sparse texture features.

Wenjia Xu, Jiuniu Wang, Yirong Wu

Urban region function recognition plays a vital character in monitoring and managing the limited urban areas. Since urban functions are complex and full of social-economic properties, simply using remote sensing~(RS) images equipped with physical and optical information cannot completely solve the classification task. On the other hand, with the development of mobile communication and the internet, the acquisition of geospatial big data~(GBD) becomes possible. In this paper, we propose a Multi-dimension Feature Learning Model~(MDFL) using high-dimensional GBD data in conjunction with RS images for urban region function recognition. When extracting multi-dimension features, our model considers the user-related information modeled by their activity, as well as the region-based information abstracted from the region graph. Furthermore, we propose a decision fusion network that integrates the decisions from several neural networks and machine learning classifiers, and the final decision is made considering both the visual cue from the RS images and the social information from the GBD data. Through quantitative evaluation, we demonstrate that our model achieves overall accuracy at 92.75, outperforming the state-of-the-art by 10 percent.

Yiran Huang, Karsten Roth, Quentin Bouniot et al.

Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do transformers learn to associate information across modalities from in-context examples? We investigate this question through controlled experiments on small transformers trained on synthetic classification tasks, enabling precise manipulation of data statistics and model architecture. We begin by revisiting core principles of unimodal ICL in modern transformers. While several prior findings replicate, we find that Rotary Position Embeddings (RoPE) increases the data complexity threshold for ICL. Extending to the multimodal setting reveals a fundamental learning asymmetry: when pretrained on high-diversity data from a primary modality, surprisingly low data complexity in the secondary modality suffices for multimodal ICL to emerge. Mechanistic analysis shows that both settings rely on an induction-style mechanism that copies labels from matching in-context exemplars; multimodal training refines and extends these circuits across modalities. Our findings provide a mechanistic foundation for understanding multimodal ICL in modern transformers and introduce a controlled testbed for future investigation.

Yiran Huang, Lukas Thede, Massimiliano Mancini et al.

While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment challenges on resource-constrained edge devices. Current parameter reduction techniques primarily involve training LVLMs from small language models, but these methods offer limited flexibility and remain computationally intensive. We study a complementary route: compressing existing LVLMs by applying structured pruning to the language model backbone, followed by lightweight recovery training. Specifically, we investigate two structural pruning paradigms: layerwise and widthwise pruning, and pair them with supervised finetuning and knowledge distillation on logits and hidden states. Additionally, we assess the feasibility of conducting recovery training with only a small fraction of the available data. Our results show that widthwise pruning generally maintains better performance in low-resource scenarios, where computational resources are limited or there is insufficient finetuning data. As for the recovery training, finetuning only the multimodal projector is sufficient at small compression levels. Furthermore, a combination of supervised finetuning and hidden-state distillation yields optimal recovery across various pruning levels. Notably, effective recovery can be achieved using just 5% of the original data, while retaining over 95% of the original performance. Through empirical study on three representative LVLM families ranging from 3B to 7B parameters, this study offers actionable insights for practitioners to compress LVLMs without extensive computation resources or sufficient data. The code base is available at https://github.com/YiranHuangIrene/VLMCompression.git.

Zhiwei Wei, Yi Xiao, Wenjia Xu et al.

Effective building pattern recognition is critical for understanding urban form, automating map generalization, and visualizing 3D city models. Most existing studies use object-independent methods based on visual perception rules and proximity graph models to extract patterns. However, because human vision is a part-based system, pattern recognition may require decomposing shapes into parts or grouping them into clusters. Existing methods may not recognize all visually aware patterns, and the proximity graph model can be inefficient. To improve efficiency and effectiveness, we integrate multi-scale data using a knowledge graph, focusing on the recognition of C-shaped building patterns. First, we use a property graph to represent the relationships between buildings within and across different scales involved in C-shaped building pattern recognition. Next, we store this knowledge graph in a graph database and convert the rules for C-shaped pattern recognition and enrichment into query conditions. Finally, we recognize and enrich C-shaped building patterns using rule-based reasoning in the built knowledge graph. We verify the effectiveness of our method using multi-scale data with three levels of detail (LODs) collected from the Gaode Map. Our results show that our method achieves a higher recall rate of 26.4% for LOD1, 20.0% for LOD2, and 9.1% for LOD3 compared to existing approaches. We also achieve recognition efficiency improvements of 0.91, 1.37, and 9.35 times, respectively.

Zhiwei Wei, Yuxing Liu, Hua Liao et al.

Map environments provide a fundamental medium for representing spatial structure. Understanding how foundation model (FM) agents understand and act in such environments is therefore critical for enabling reliable map-based reasoning and applications. However, most existing evaluations of spatial ability in FMs rely on static map inputs or text-based queries, overlooking the interactive and experience-driven nature of spatial understanding.In this paper, we propose an interactive evaluation framework to analyze how FM agents explore, remember, and reason in symbolic map environments. Agents incrementally explore partially observable grid-based maps consisting of roads, intersections, and points of interest (POIs), receiving only local observations at each step. Spatial understanding is then evaluated using six kinds of spatial tasks. By systematically varying exploration strategies, memory representations, and reasoning schemes across multiple foundation models, we reveal distinct functional roles of these components. Exploration primarily affects experience acquisition but has a limited impact on final reasoning accuracy. In contrast, memory representation plays a central role in consolidating spatial experience, with structured memories particularly sequential and graph-based representations, substantially improving performance on structure-intensive tasks such as path planning. Reasoning schemes further shape how stored spatial knowledge is used, with advanced prompts supporting more effective multi-step inference. We further observe that spatial reasoning performance saturates across model versions and scales beyond a certain capability threshold, indicating that improvements in map-based spatial understanding require mechanisms tailored to spatial representation and reasoning rather than scaling alone.

Yujie Li, Wenjia Xu, Guangzuo Li et al.

The domain gap between remote sensing imagery and natural images has recently received widespread attention and Vision-Language Models (VLMs) have demonstrated excellent generalization performance in remote sensing multimodal tasks. However, current research is still limited in exploring how remote sensing VLMs handle different types of visual inputs. To bridge this gap, we introduce \textbf{UniRS}, the first vision-language model \textbf{uni}fying multi-temporal \textbf{r}emote \textbf{s}ensing tasks across various types of visual input. UniRS supports single images, dual-time image pairs, and videos as input, enabling comprehensive remote sensing temporal analysis within a unified framework. We adopt a unified visual representation approach, enabling the model to accept various visual inputs. For dual-time image pair tasks, we customize a change extraction module to further enhance the extraction of spatiotemporal features. Additionally, we design a prompt augmentation mechanism tailored to the model's reasoning process, utilizing the prior knowledge of the general-purpose VLM to provide clues for UniRS. To promote multi-task knowledge sharing, the model is jointly fine-tuned on a mixed dataset. Experimental results show that UniRS achieves state-of-the-art performance across diverse tasks, including visual question answering, change captioning, and video scene classification, highlighting its versatility and effectiveness in unifying these multi-temporal remote sensing tasks. Our code and dataset will be released soon.

Wenjia Xu, Zijian Yu, Boyang Mu et al.

The unprecedented advancements in Multimodal Large Language Models (MLLMs) have demonstrated strong potential in interacting with humans through both language and visual inputs to perform downstream tasks such as visual question answering and scene understanding. However, these models are constrained to basic instruction-following or descriptive tasks, facing challenges in complex real-world remote sensing applications that require specialized tools and knowledge. To address these limitations, we propose RS-Agent, an AI agent designed to interact with human users and autonomously leverage specialized models to address the demands of real-world remote sensing applications. RS-Agent integrates four key components: a Central Controller based on large language models, a dynamic toolkit for tool execution, a Solution Space for task-specific expert guidance, and a Knowledge Space for domain-level reasoning, enabling it to interpret user queries and orchestrate tools for accurate remote sensing task. We introduce two novel mechanisms: Task-Aware Retrieval, which improves tool selection accuracy through expert-guided planning, and DualRAG, a retrieval-augmented generation method that enhances knowledge relevance through weighted, dual-path retrieval. RS-Agent supports flexible integration of new tools and is compatible with both open-source and proprietary LLMs. Extensive experiments across 9 datasets and 18 remote sensing tasks demonstrate that RS-Agent significantly outperforms state-of-the-art MLLMs, achieving over 95% task planning accuracy and delivering superior performance in tasks such as scene classification, object counting, and remote sensing visual question answering. Our work presents RS-Agent as a robust and extensible framework for advancing intelligent automation in remote sensing analysis.

Zhiwei Wei, Nai Yang, Wenjia Xu et al.

The grid map, often referred to as the tile map, stands as a vital tool in geospatial visualization, possessing unique attributes that differentiate it from more commonly known techniques such as choropleths and cartograms. It transforms geographic regions into grids, which requires the displacement of both region centroids and boundary nodes to establish a coherent grid arrangement. However, existing approaches typically displace region centroids and boundary nodes separately, potentially resulting in self-intersected boundaries and compromised relative orientation relations between regions. In this paper, we introduce a novel approach that leverages the Snake displacement algorithm from cartographic generalization to concurrently displace region centroids and boundary nodes. The revised Constrained Delaunay triangulation (CDT) is employed to represent the relations between regions and serves as a structural foundation for the Snake algorithm. Forces for displacing the region centroids into a grid-like pattern are then computed. These forces are iteratively applied within the Snake model until a satisfactory new boundary is achieved. Subsequently, the grid map is created by aligning the grids with the newly generated boundary, utilizing a one-to-one match algorithm to assign each region to a specific grid. Experimental results demonstrate that the proposed approach excels in maintaining the relative orientation and global shape of regions, albeit with a potential increase in local location deviations. We also present two strategies aligned with existing approaches to generate diverse grid maps for user preferences. Further details and resources are available on our project website: https://github.com/TrentonWei/DorlingMap.git.

Yao Rong, Wenjia Xu, Zeynep Akata et al.

The way humans attend to, process and classify a given image has the potential to vastly benefit the performance of deep learning models. Exploiting where humans are focusing can rectify models when they are deviating from essential features for correct decisions. To validate that human attention contains valuable information for decision-making processes such as fine-grained classification, we compare human attention and model explanations in discovering important features. Towards this goal, we collect human gaze data for the fine-grained classification dataset CUB and build a dataset named CUB-GHA (Gaze-based Human Attention). Furthermore, we propose the Gaze Augmentation Training (GAT) and Knowledge Fusion Network (KFN) to integrate human gaze knowledge into classification models. We implement our proposals in CUB-GHA and the recently released medical dataset CXR-Eye of chest X-ray images, which includes gaze data collected from a radiologist. Our result reveals that integrating human attention knowledge benefits classification effectively, e.g. improving the baseline by 4.38% on CXR. Hence, our work provides not only valuable insights into understanding human attention in fine-grained classification, but also contributes to future research in integrating human gaze with computer vision tasks. CUB-GHA and code are available at https://github.com/yaorong0921/CUB-GHA.

Linrui Shou, Zilang Chen, Wenjia Xu et al.

We present a zero-shot deformation reconstruction framework for soft robots that operates without any visual supervision at inference time. In this work, zero-shot deformation reconstruction is defined as the ability to infer object-wide deformations on previously unseen soft robots without collecting object-specific deformation data or performing any retraining during deployment. Our method assumes access to a static geometric proxy of the undeformed object, which can be obtained from a STL model. During operation, the system relies exclusively on tactile sensing, enabling camera-free deformation inference. The proposed framework integrates a flexible piezoresistive sensor array with a geometry-aware, cage-based 3D Gaussian deformation model. Local tactile measurements are mapped to low-dimensional cage control signals and propagated to dense Gaussian primitives to generate globally consistent shape deformations. A graph attention network regresses cage displacements from tactile input, enforcing spatial smoothness and structural continuity via boundary-aware propagation. Given only a nominal geometric proxy and real-time tactile signals, the system performs zero-shot deformation reconstruction of unseen soft robots in bending and twisting motions, while rendering photorealistic RGB in real time. It achieves 0.67 IoU, 0.65 SSIM, and 3.48 mm Chamfer distance, demonstrating strong zero-shot generalization through explicit coupling of tactile sensing and structured geometric deformation.

Wenjia Xu, Yaxuan Yao, Jiaqi Cao et al.

The application of unmanned aerial vehicles (UAV) has been widely extended recently. It is crucial to ensure accurate latitude and longitude coordinates for UAVs, especially when the global navigation satellite systems (GNSS) are disrupted and unreliable. Existing visual localization methods achieve autonomous visual localization without error accumulation by matching the ground-down view image of UAV with the ortho satellite maps. However, collecting UAV ground-down view images across diverse locations is costly, leading to a scarcity of large-scale datasets for real-world scenarios. Existing datasets for UAV visual localization are often limited to small geographic areas or are focused only on urban regions with distinct textures. To address this, we define the UAV visual localization task by determining the UAV's real position coordinates on a large-scale satellite map based on the captured ground-down view. In this paper, we present a large-scale dataset, UAV-VisLoc, to facilitate the UAV visual localization task. This dataset comprises images from diverse drones across 11 locations in China, capturing a range of topographical features. The dataset features images from fixed-wing drones and multi-terrain drones, captured at different altitudes and orientations. Our dataset includes 6,742 drone images and 11 satellite maps, with metadata such as latitude, longitude, altitude, and capture date. Our dataset is tailored to support both the training and testing of models by providing a diverse and extensive data.

Wenjia Xu, Jiuniu Wang, Zhiwei Wei et al.

Deep neural networks have achieved promising progress in remote sensing (RS) image classification, for which the training process requires abundant samples for each class. However, it is time-consuming and unrealistic to annotate labels for each RS category, given the fact that the RS target database is increasing dynamically. Zero-shot learning (ZSL) allows for identifying novel classes that are not seen during training, which provides a promising solution for the aforementioned problem. However, previous ZSL models mainly depend on manually-labeled attributes or word embeddings extracted from language models to transfer knowledge from seen classes to novel classes. Besides, pioneer ZSL models use convolutional neural networks pre-trained on ImageNet, which focus on the main objects appearing in each image, neglecting the background context that also matters in RS scene classification. To address the above problems, we propose to collect visually detectable attributes automatically. We predict attributes for each class by depicting the semantic-visual similarity between attributes and images. In this way, the attribute annotation process is accomplished by machine instead of human as in other methods. Moreover, we propose a Deep Semantic-Visual Alignment (DSVA) that take advantage of the self-attention mechanism in the transformer to associate local image regions together, integrating the background context information for prediction. The DSVA model further utilizes the attribute attention maps to focus on the informative image regions that are essential for knowledge transfer in ZSL, and maps the visual images into attribute space to perform ZSL classification. With extensive experiments, we show that our model outperforms other state-of-the-art models by a large margin on a challenging large-scale RS scene classification benchmark.

Song Zhang, Zhiwei Wei, Wenjia Xu et al.

3D terrain reconstruction with remote sensing imagery achieves cost-effective and large-scale earth observation and is crucial for safeguarding natural disasters, monitoring ecological changes, and preserving the environment.Recently, learning-based multi-view stereo~(MVS) methods have shown promise in this task. However, these methods simply modify the general learning-based MVS framework for height estimation, which overlooks the terrain characteristics and results in insufficient accuracy. Considering that the Earth's surface generally undulates with no drastic changes and can be measured by slope, integrating slope considerations into MVS frameworks could enhance the accuracy of terrain reconstructions. To this end, we propose an end-to-end slope-aware height estimation network named TS-SatMVSNet for large-scale remote sensing terrain reconstruction.To effectively obtain the slope representation, drawing from mathematical gradient concepts, we innovatively proposed a height-based slope calculation strategy to first calculate a slope map from a height map to measure the terrain undulation. To fully integrate slope information into the MVS pipeline, we separately design two slope-guided modules to enhance reconstruction outcomes at both micro and macro levels. Specifically, at the micro level, we designed a slope-guided interval partition module for refined height estimation using slope values. At the macro level, a height correction module is proposed, using a learnable Gaussian smoothing operator to amend the inaccurate height values. Additionally, to enhance the efficacy of height estimation, we proposed a slope direction loss for implicitly optimizing height estimation results. Extensive experiments on the WHU-TLC dataset and MVS3D dataset show that our proposed method achieves state-of-the-art performance and demonstrates competitive generalization ability.

Yujie Li, Wenjia Xu, Yuanben Zhang et al.

Bi-temporal satellite imagery supports critical applications such as urban development monitoring and disaster assessment. Although powerful multimodal large language models (MLLMs) have been applied in bi-temporal change analysis, previous methods process image pairs through direct concatenation, inadequately modeling temporal correlations and spatial semantic changes. This deficiency hampers visual-semantic alignment in change understanding, thereby constraining the overall effectiveness of current approaches. To address this gap, we propose BTCChat, a multi-temporal MLLM with advanced bi-temporal change understanding capability. BTCChat supports bi-temporal change captioning and retains single-image interpretation capability. To better capture temporal features and spatial semantic changes in image pairs, we design a Change Extraction module. Moreover, to enhance the model's attention to spatial details, we introduce a Prompt Augmentation mechanism, which incorporates contextual clues into the prompt to enhance model performance. Experimental results demonstrate that BTCChat achieves state-of-the-art performance on change captioning and visual question answering tasks.

Yiran Huang, Lukas Thede, Massimiliano Mancini et al.

While Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose significant barriers to practical deployment. Current parameter reduction techniques primarily involve training MLLMs from Small Language Models (SLMs), but these methods offer limited flexibility and remain computationally intensive. To address this gap, we propose to directly compress existing MLLMs through structural pruning combined with efficient recovery training. Specifically, we investigate two structural pruning paradigms--layerwise and widthwise pruning--applied to the language model backbone of MLLMs, alongside supervised finetuning and knowledge distillation. Additionally, we assess the feasibility of conducting recovery training with only a small fraction of the available data. Our results show that widthwise pruning generally maintains better performance in low-resource scenarios with limited computational resources or insufficient finetuning data. As for the recovery training, finetuning only the multimodal projector is sufficient at small compression levels (< 20%). Furthermore, a combination of supervised finetuning and hidden-state distillation yields optimal recovery across various pruning levels. Notably, effective recovery can be achieved with as little as 5% of the original training data, while retaining over 95% of the original performance. Through empirical study on two representative MLLMs, i.e., LLaVA-v1.5-7B and Bunny-v1.0-3B, this study offers actionable insights for practitioners aiming to compress MLLMs effectively without extensive computation resources or sufficient data.

Jiuniu Wang, Wenjia Xu, Qingzhong Wang et al.

Recent advances in image captioning have focused on enhancing accuracy by substantially increasing the dataset and model size. While conventional captioning models exhibit high performance on established metrics such as BLEU, CIDEr, and SPICE, the capability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employed contrastive learning or re-weighted the ground-truth captions. However, these approaches often overlook the relationships among objects in a similar image group (e.g., items or properties within the same album or fine-grained events). In this paper, we introduce a novel approach to enhance the distinctiveness of image captions, namely Group-based Differential Distinctive Captioning Method, which visually compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we introduce a Group-based Differential Memory Attention (GDMA) module, designed to identify and emphasize object features in an image that are uniquely distinguishable within its image group, i.e., those exhibiting low similarity with objects in other images. This mechanism ensures that such unique object features are prioritized during caption generation for the image, thereby enhancing the distinctiveness of the resulting captions. To further refine this process, we select distinctive words from the ground-truth captions to guide both the language decoder and the GDMA module. Additionally, we propose a new evaluation metric, the Distinctive Word Rate (DisWordRate), to quantitatively assess caption distinctiveness. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves state-of-the-art performance on distinctiveness while not excessively sacrificing accuracy...

Zhiwei Wei, Nai Yang, Wenjia Xu et al.

In three-dimensional geographical scenes, adding labels with leader lines to point features can significantly improve their visibility. Leadered labels have a large degree of freedom in position con-figuration, but existing methods are mostly based on limited position candidate models, which not only fail to effectively utilize the map space but also make it difficult to consider the relative relationships between labels. Therefore, we conceptualize the dynamic configuration process of computing label positions as akin to solving a map displacement problem. We use a triangulated graph to delineate spatial relationships among labels and calculate the forces exerted on labels considering the constraints associated with point feature labels. Then we use the Beams Displacement Method to iteratively calculate new positions for the labels. Our experimental outcomes demonstrate that this method effectively mitigates label overlay issues while maintaining minimal average directional deviation between adjacent labels. Furthermore, this method is adaptable to various types of leader line labels. Meanwhile, we also discuss the block processing strategy to improve the efficiency of label configuration and analyze the impact of different proximity graphs.

Jiuniu Wang, Wenjia Xu, Qingzhong Wang et al.

Describing images using natural language is widely known as image captioning, which has made consistent progress due to the development of computer vision and natural language generation techniques. Though conventional captioning models achieve high accuracy based on popular metrics, i.e., BLEU, CIDEr, and SPICE, the ability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employ contrastive learning or re-weighted the ground-truth captions, which focuses on one single input image. However, the relationships between objects in a similar image group (e.g., items or properties within the same album or fine-grained events) are neglected. In this paper, we improve the distinctiveness of image captions using a Group-based Distinctive Captioning Model (GdisCap), which compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we propose a group-based memory attention (GMA) module, which stores object features that are unique among the image group (i.e., with low similarity to objects in other images). These unique object features are highlighted when generating captions, resulting in more distinctive captions. Furthermore, the distinctive words in the ground-truth captions are selected to supervise the language decoder and GMA. Finally, we propose a new evaluation metric, distinctive word rate (DisWordRate) to measure the distinctiveness of captions. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves the state-of-the-art performance on both accuracy and distinctiveness. Results of a user study agree with the quantitative evaluation and demonstrate the rationality of the new metric DisWordRate.

Wenjia Xu, Guangluan Xu, Yang Wang et al.

Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification. However, existing methods based on the neural network usually have small receptive fields and ignore the image detail. We propose a novel method named deep memory connected network (DMCN) based on a convolutional neural network to reconstruct high-quality super-resolution images. We build local and global memory connections to combine image detail with environmental information. To further reduce parameters and ease time-consuming, we propose downsampling units, shrinking the spatial size of feature maps. We test DMCN on three remote sensing datasets with different spatial resolution. Experimental results indicate that our method yields promising improvements in both accuracy and visual performance over the current state-of-the-art.

Wenjia Xu, Jiuniu Wang, Yang Wang et al.

Image classification models have achieved satisfactory performance on many datasets, sometimes even better than human. However, The model attention is unclear since the lack of interpretability. This paper investigates the fidelity and interpretability of model attention. We propose an Explainable Attribute-based Multi-task (EAT) framework to concentrate the model attention on the discriminative image area and make the attention interpretable. We introduce attributes prediction to the multi-task learning network, helping the network to concentrate attention on the foreground objects. We generate attribute-based textual explanations for the network and ground the attributes on the image to show visual explanations. The multi-model explanation can not only improve user trust but also help to find the weakness of network and dataset. Our framework can be generalized to any basic model. We perform experiments on three datasets and five basic models. Results indicate that the EAT framework can give multi-modal explanations that interpret the network decision. The performance of several recognition approaches is improved by guiding network attention.

Jiuniu Wang, Wenjia Xu, Xingyu Fu et al.

The question answering system can answer questions from various fields and forms with deep neural networks, but it still lacks effective ways when facing multiple evidences. We introduce a new model called SRQA, which means Synthetic Reader for Factoid Question Answering. This model enhances the question answering system in the multi-document scenario from three aspects: model structure, optimization goal, and training method, corresponding to Multilayer Attention (MA), Cross Evidence (CE), and Adversarial Training (AT) respectively. First, we propose a multilayer attention network to obtain a better representation of the evidences. The multilayer attention mechanism conducts interaction between the question and the passage within each layer, making the token representation of evidences in each layer takes the requirement of the question into account. Second, we design a cross evidence strategy to choose the answer span within more evidences. We improve the optimization goal, considering all the answers' locations in multiple evidences as training targets, which leads the model to reason among multiple evidences. Third, adversarial training is employed to high-level variables besides the word embedding in our model. A new normalization method is also proposed for adversarial perturbations so that we can jointly add perturbations to several target variables. As an effective regularization method, adversarial training enhances the model's ability to process noisy data. Combining these three strategies, we enhance the contextual representation and locating ability of our model, which could synthetically extract the answer span from several evidences. We perform SRQA on the WebQA dataset, and experiments show that our model outperforms the state-of-the-art models (the best fuzzy score of our model is up to 78.56%, with an improvement of about 2%).

Jiuniu Wang, Wenjia Xu, Xingyu Fu et al.

Named Entity Recognition (NER) is a challenging task that extracts named entities from unstructured text data, including news, articles, social comments, etc. The NER system has been studied for decades. Recently, the development of Deep Neural Networks and the progress of pre-trained word embedding have become a driving force for NER. Under such circumstances, how to make full use of the information extracted by word embedding requires more in-depth research. In this paper, we propose an Adversarial Trained LSTM-CNN (ASTRAL) system to improve the current NER method from both the model structure and the training process. In order to make use of the spatial information between adjacent words, Gated-CNN is introduced to fuse the information of adjacent words. Besides, a specific Adversarial training method is proposed to deal with the overfitting problem in NER. We add perturbation to variables in the network during the training process, making the variables more diverse, improving the generalization and robustness of the model. Our model is evaluated on three benchmarks, CoNLL-03, OntoNotes 5.0, and WNUT-17, achieving state-of-the-art results. Ablation study and case study also show that our system can converge faster and is less prone to overfitting.

Wenjia Xu, Yongqin Xian, Jiuniu Wang et al.

From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes, we argue that an image representation with integrated attribute localization ability would be beneficial for zero-shot learning. To this end, we propose a novel zero-shot representation learning framework that jointly learns discriminative global and local features using only class-level attributes. While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate features. We show that our locality augmented image representations achieve a new state-of-the-art on three zero-shot learning benchmarks. As an additional benefit, our model points to the visual evidence of the attributes in an image, e.g. for the CUB dataset, confirming the improved attribute localization ability of our image representation.

Jiuniu Wang, Wenjia Xu, Qingzhong Wang et al.

A wide range of image captioning models has been developed, achieving significant improvement based on popular metrics, such as BLEU, CIDEr, and SPICE. However, although the generated captions can accurately describe the image, they are generic for similar images and lack distinctiveness, i.e., cannot properly describe the uniqueness of each image. In this paper, we aim to improve the distinctiveness of image captions through training with sets of similar images. First, we propose a distinctiveness metric -- between-set CIDEr (CIDErBtw) to evaluate the distinctiveness of a caption with respect to those of similar images. Our metric shows that the human annotations of each image are not equivalent based on distinctiveness. Thus we propose several new training strategies to encourage the distinctiveness of the generated caption for each image, which are based on using CIDErBtw in a weighted loss function or as a reinforcement learning reward. Finally, extensive experiments are conducted, showing that our proposed approach significantly improves both distinctiveness (as measured by CIDErBtw and retrieval metrics) and accuracy (e.g., as measured by CIDEr) for a wide variety of image captioning baselines. These results are further confirmed through a user study.