Jun Li

Junkai Fan, Fei Guo, Jianjun Qian et al.

Removing haze from real-world images is challenging due to unpredictable weather conditions, resulting in the misalignment of hazy and clear image pairs. In this paper, we propose an innovative dehazing framework that operates under non-aligned supervision. This framework is grounded in the atmospheric scattering model, and consists of three interconnected networks: dehazing, airlight, and transmission networks. In particular, we explore a non-alignment scenario that a clear reference image, unaligned with the input hazy image, is utilized to supervise the dehazing network. To implement this, we present a multi-scale reference loss that compares the feature representations between the referred image and the dehazed output. Our scenario makes it easier to collect hazy/clear image pairs in real-world environments, even under conditions of misalignment and shift views. To showcase the effectiveness of our scenario, we have collected a new hazy dataset including 415 image pairs captured by mobile Phone in both rural and urban areas, called "Phone-Hazy". Furthermore, we introduce a self-attention network based on mean and variance for modeling real infinite airlight, using the dark channel prior as positional guidance. Additionally, a channel attention network is employed to estimate the three-channel transmission. Experimental results demonstrate the superior performance of our framework over existing state-of-the-art techniques in the real-world image dehazing task. Phone-Hazy and code will be available at https://fanjunkai1.github.io/projectpage/NSDNet/index.html.

Kunal Chaturvedi, Ali Braytee, Jun Li et al.

This paper proposes a novel self-supervised based Cut-and-Paste GAN to perform foreground object segmentation and generate realistic composite images without manual annotations. We accomplish this goal by a simple yet effective self-supervised approach coupled with the U-Net based discriminator. The proposed method extends the ability of the standard discriminators to learn not only the global data representations via classification (real/fake) but also learn semantic and structural information through pseudo labels created using the self-supervised task. The proposed method empowers the generator to create meaningful masks by forcing it to learn informative per-pixel as well as global image feedback from the discriminator. Our experiments demonstrate that our proposed method significantly outperforms the state-of-the-art methods on the standard benchmark datasets.

Jianwen Xie, Yaxuan Zhu, Jun Li et al.

This paper studies the cooperative learning of two generative flow models, in which the two models are iteratively updated based on the jointly synthesized examples. The first flow model is a normalizing flow that transforms an initial simple density to a target density by applying a sequence of invertible transformations. The second flow model is a Langevin flow that runs finite steps of gradient-based MCMC toward an energy-based model. We start from proposing a generative framework that trains an energy-based model with a normalizing flow as an amortized sampler to initialize the MCMC chains of the energy-based model. In each learning iteration, we generate synthesized examples by using a normalizing flow initialization followed by a short-run Langevin flow revision toward the current energy-based model. Then we treat the synthesized examples as fair samples from the energy-based model and update the model parameters with the maximum likelihood learning gradient, while the normalizing flow directly learns from the synthesized examples by maximizing the tractable likelihood. Under the short-run non-mixing MCMC scenario, the estimation of the energy-based model is shown to follow the perturbation of maximum likelihood, and the short-run Langevin flow and the normalizing flow form a two-flow generator that we call CoopFlow. We provide an understating of the CoopFlow algorithm by information geometry and show that it is a valid generator as it converges to a moment matching estimator. We demonstrate that the trained CoopFlow is capable of synthesizing realistic images, reconstructing images, and interpolating between images.

Zixin Shu, Rui Hua, Dengying Yan et al.

Symptom phenotypes are one of the key types of manifestations for diagnosis and treatment of various disease conditions. However, the diversity of symptom terminologies is one of the major obstacles hindering the analysis and knowledge sharing of various types of symptom-related medical data particularly in the fields of Traditional Chinese Medicine (TCM). Objective: This study aimed to construct an Integrated Ontology of symptom phenotypes (ISPO) to support the data mining of Chinese EMRs and real-world study in TCM field. Methods: To construct an integrated ontology of symptom phenotypes (ISPO), we manually annotated classical TCM textbooks and large-scale Chinese electronic medical records (EMRs) to collect symptom terms with support from a medical text annotation system. Furthermore, to facilitate the semantic interoperability between different terminologies, we incorporated public available biomedical vocabularies by manual mapping between Chinese terms and English terms with cross-references to source vocabularies. In addition, we evaluated the ISPO using independent clinical EMRs to provide a high-usable medical ontology for clinical data analysis. Results: By integrating 78,696 inpatient cases of EMRs, 5 biomedical vocabularies, 21 TCM books and dictionaries, ISPO provides 3,147 concepts, 23,475 terms, and 55,552 definition or contextual texts. Adhering to the taxonomical structure of the related anatomical systems of symptom phenotypes, ISPO provides 12 top-level categories and 79 middle-level sub-categories. The validation of data analysis showed the ISPO has a coverage rate of 95.35%, 98.53% and 92.66% for symptom terms with occurrence rates of 0.5% in additional three independent curated clinical datasets, which can demonstrate the significant value of ISPO in mapping clinical terms to ontologies.

Jiawei Zhang, Jun Li, Reachsak Ly et al.

For structural health monitoring, continuous and automatic crack detection has been a challenging problem. This study is conducted to propose a framework of automatic crack segmentation from high-resolution images containing crack information about steel box girders of bridges. Considering the multi-scale feature of cracks, convolutional neural network architecture of Feature Pyramid Networks (FPN) for crack detection is proposed. As for input, 120 raw images are processed via two approaches (shrinking the size of images and splitting images into sub-images). Then, models with the proposed structure of FPN for crack detection are developed. The result shows all developed models can automatically detect the cracks at the raw images. By shrinking the images, the computation efficiency is improved without decreasing accuracy. Because of the separable characteristic of crack, models using the splitting method provide more accurate crack segmentations than models using the resizing method. Therefore, for high-resolution images, the FPN structure coupled with the splitting method is an promising solution for the crack segmentation and detection.

Kun Wang, Zhiqiang Yan, Junkai Fan et al.

Depth completion endeavors to reconstruct a dense depth map from sparse depth measurements, leveraging the information provided by a corresponding color image. Existing approaches mostly hinge on single-scale propagation strategies that iteratively ameliorate initial coarse depth estimates through pixel-level message passing. Despite their commendable outcomes, these techniques are frequently hampered by computational inefficiencies and a limited grasp of scene context. To circumvent these challenges, we introduce LP-Net, an innovative framework that implements a multi-scale, progressive prediction paradigm based on Laplacian Pyramid decomposition. Diverging from propagation-based approaches, LP-Net initiates with a rudimentary, low-resolution depth prediction to encapsulate the global scene context, subsequently refining this through successive upsampling and the reinstatement of high-frequency details at incremental scales. We have developed two novel modules to bolster this strategy: 1) the Multi-path Feature Pyramid module, which segregates feature maps into discrete pathways, employing multi-scale transformations to amalgamate comprehensive spatial information, and 2) the Selective Depth Filtering module, which dynamically learns to apply both smoothness and sharpness filters to judiciously mitigate noise while accentuating intricate details. By integrating these advancements, LP-Net not only secures state-of-the-art (SOTA) performance across both outdoor and indoor benchmarks such as KITTI, NYUv2, and TOFDC, but also demonstrates superior computational efficiency. At the time of submission, LP-Net ranks 1st among all peer-reviewed methods on the official KITTI leaderboard.

Xing Zi, Jinghao Xiao, Yunxiao Shi et al.

Visual Question Answering (VQA) in remote sensing (RS) is pivotal for interpreting Earth observation data. However, existing RS VQA datasets are constrained by limitations in annotation richness, question diversity, and the assessment of specific reasoning capabilities. This paper introduces RSVLM-QA dataset, a new large-scale, content-rich VQA dataset for the RS domain. RSVLM-QA is constructed by integrating data from several prominent RS segmentation and detection datasets: WHU, LoveDA, INRIA, and iSAID. We employ an innovative dual-track annotation generation pipeline. Firstly, we leverage Large Language Models (LLMs), specifically GPT-4.1, with meticulously designed prompts to automatically generate a suite of detailed annotations including image captions, spatial relations, and semantic tags, alongside complex caption-based VQA pairs. Secondly, to address the challenging task of object counting in RS imagery, we have developed a specialized automated process that extracts object counts directly from the original segmentation data; GPT-4.1 then formulates natural language answers from these counts, which are paired with preset question templates to create counting QA pairs. RSVLM-QA comprises 13,820 images and 162,373 VQA pairs, featuring extensive annotations and diverse question types. We provide a detailed statistical analysis of the dataset and a comparison with existing RS VQA benchmarks, highlighting the superior depth and breadth of RSVLM-QA's annotations. Furthermore, we conduct benchmark experiments on Six mainstream Vision Language Models (VLMs), demonstrating that RSVLM-QA effectively evaluates and challenges the understanding and reasoning abilities of current VLMs in the RS domain. We believe RSVLM-QA will serve as a pivotal resource for the RS VQA and VLM research communities, poised to catalyze advancements in the field.

Xing Zi, Tengjun Ni, Xianjing Fan et al.

Accurate and automated captioning of aerial imagery is crucial for applications like environmental monitoring, urban planning, and disaster management. However, this task remains challenging due to complex spatial semantics and domain variability. To address these issues, we introduce \textbf{AeroLite}, a lightweight, tag-guided captioning framework designed to equip small-scale language models (1--3B parameters) with robust and interpretable captioning capabilities specifically for remote sensing images. \textbf{AeroLite} leverages GPT-4o to generate a large-scale, semantically rich pseudo-caption dataset by integrating multiple remote sensing benchmarks, including DLRSD, iSAID, LoveDA, WHU, and RSSCN7. To explicitly capture key semantic elements such as orientation and land-use types, AeroLite employs natural language processing techniques to extract relevant semantic tags. These tags are then learned by a dedicated multi-label CLIP encoder, ensuring precise semantic predictions. To effectively fuse visual and semantic information, we propose a novel bridging multilayer perceptron (MLP) architecture, aligning semantic tags with visual embeddings while maintaining minimal computational overhead. AeroLite's flexible design also enables seamless integration with various pretrained large language models. We adopt a two-stage LoRA-based training approach: the initial stage leverages our pseudo-caption dataset to capture broad remote sensing semantics, followed by fine-tuning on smaller, curated datasets like UCM and Sydney Captions to refine domain-specific alignment. Experimental evaluations demonstrate that AeroLite surpasses significantly larger models (e.g., 13B parameters) in standard captioning metrics, including BLEU and METEOR, while maintaining substantially lower computational costs.

Xing Zi, Kairui Jin, Xian Tao et al.

Pixel-level segmentation is essential in remote sensing, where foundational vision models like CLIP and Segment Anything Model(SAM) have demonstrated significant capabilities in zero-shot segmentation tasks. Despite their advances, challenges specific to remote sensing remain substantial. Firstly, The SAM without clear prompt constraints, often generates redundant masks, and making post-processing more complex. Secondly, the CLIP model, mainly designed for global feature alignment in foundational models, often overlooks local objects crucial to remote sensing. This oversight leads to inaccurate recognition or misplaced focus in multi-target remote sensing imagery. Thirdly, both models have not been pre-trained on multi-scale aerial views, increasing the likelihood of detection failures. To tackle these challenges, we introduce the innovative VTPSeg pipeline, utilizing the strengths of Grounding DINO, CLIP, and SAM for enhanced open-vocabulary image segmentation. The Grounding DINO+(GD+) module generates initial candidate bounding boxes, while the CLIP Filter++(CLIP++) module uses a combination of visual and textual prompts to refine and filter out irrelevant object bounding boxes, ensuring that only pertinent objects are considered. Subsequently, these refined bounding boxes serve as specific prompts for the FastSAM model, which executes precise segmentation. Our VTPSeg is validated by experimental and ablation study results on five popular remote sensing image segmentation datasets.

Zixuan Song, Jun Li

Deep neural networks (DNNs) are famous for their high prediction accuracy, but they are also known for their black-box nature and poor interpretability. We consider the problem of variable selection, that is, selecting the input variables that have significant predictive power on the output, in DNNs. We propose a backward elimination procedure called SurvNet, which is based on a new measure of variable importance that applies to a wide variety of networks. More importantly, SurvNet is able to estimate and control the false discovery rate of selected variables, while no existing methods provide such a quality control. Further, SurvNet adaptively determines how many variables to eliminate at each step in order to maximize the selection efficiency. To study its validity, SurvNet is applied to image data and gene expression data, as well as various simulation datasets.

Jun Li, Xun Lin, Xiaoguang Rui et al.

Distance metric learning is successful in discovering intrinsic relations in data. However, most algorithms are computationally demanding when the problem size becomes large. In this paper, we propose a discriminative metric learning algorithm, and develop a distributed scheme learning metrics on moderate-sized subsets of data, and aggregating the results into a global solution. The technique leverages the power of parallel computation. The algorithm of the aggregated distance metric learning (ADML) scales well with the data size and can be controlled by the partition. We theoretically analyse and provide bounds for the error induced by the distributed treatment. We have conducted experimental evaluation of ADML, both on specially designed tests and on practical image annotation tasks. Those tests have shown that ADML achieves the state-of-the-art performance at only a fraction of the cost incurred by most existing methods.

Guoliang Kang, Jun Li, Dacheng Tao

Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit's contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines $L_0$, $L_1$ and $L_2$ regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture.

Ancheng Lin, Jun Li, Zhenyuan Ma

In this work, we investigate the following: 1) how the routing affects the CapsNet model fitting; 2) how the representation using capsules helps discover global structures in data distribution, and; 3) how the learned data representation adapts and generalizes to new tasks. Our investigation yielded the results some of which have been mentioned in the original paper of CapsNet, they are: 1) the routing operation determines the certainty with which a layer of capsules pass information to the layer above and the appropriate level of certainty is related to the model fitness; 2) in a designed experiment using data with a known 2D structure, capsule representations enable a more meaningful 2D manifold embedding than neurons do in a standard convolutional neural network (CNN), and; 3) compared with neurons of the standard CNN, capsules of successive layers are less coupled and more adaptive to new data distribution.

Jun Li, Chang Xu, Wankou Yang et al.

Conventional multi-view re-ranking methods usually perform asymmetrical matching between the region of interest (ROI) in the query image and the whole target image for similarity computation. Due to the inconsistency in the visual appearance, this practice tends to degrade the retrieval accuracy particularly when the image ROI, which is usually interpreted as the image objectness, accounts for a smaller region in the image. Since Privileged Information (PI), which can be viewed as the image prior, enables well characterizing the image objectness, we are aiming at leveraging PI for further improving the performance of the multi-view re-ranking accuracy in this paper. Towards this end, we propose a discriminative multi-view re-ranking approach in which both the original global image visual contents and the local auxiliary PI features are simultaneously integrated into a unified training framework for generating the latent subspaces with sufficient discriminating power. For the on-the-fly re-ranking, since the multi-view PI features are unavailable, we only project the original multi-view image representations onto the latent subspace, and thus the re-ranking can be achieved by computing and sorting the distances from the multi-view embeddings to the separating hyperplane. Extensive experimental evaluations on the two public benchmarks Oxford5k and Paris6k reveal our approach provides further performance boost for accurate image re-ranking, whilst the comparative study demonstrates the advantage of our method against other multi-view re-ranking methods.

Shuo Chen, Chen Gong, Jian Yang et al.

In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However, the trained models often fail to produce reliable distances on the ambiguous test pairs due to the distribution bias between training set and test set. To address this problem, the Adversarial Metric Learning (AML) is proposed in this paper, which automatically generates adversarial pairs to remedy the distribution bias and facilitate robust metric learning. Specifically, AML consists of two adversarial stages, i.e. confusion and distinguishment. In confusion stage, the ambiguous but critical adversarial data pairs are adaptively generated to mislead the learned metric. In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs. Thanks to the challenges posed by the confusion stage in such competing process, the AML model is able to grasp plentiful difficult knowledge that has not been contained by the original training pairs, so the discriminability of AML can be significantly improved. The entire model is formulated into optimization framework, of which the global convergence is theoretically proved. The experimental results on toy data and practical datasets clearly demonstrate the superiority of AML to the representative state-of-the-art metric learning methodologies.