arXiv subjects

Wenjing Li

Publications and source records attributed to Wenjing Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery

In this paper, we investigate a practical yet challenging task: On-the-fly Category Discovery (OCD). This task focuses on the online identification of newly arriving stream data that may belong to both known and unknown categories, utilizing the category knowledge from only labeled data. Existing OCD methods are devoted to fully mining transferable knowledge from only labeled data. However, the transferability learned by these methods is limited because the knowledge contained in known categories is often insufficient, especially when few annotated data/categories are available in fine-grained recognition. To mitigate this limitation, we propose a diffusion-based OCD framework, dubbed DiffGRE, which integrates Generation, Refinement, and Encoding in a multi-stage fashion. Specifically, we first design an attribute-composition generation method based on cross-image interpolation in the diffusion latent space to synthesize novel samples. Then, we propose a diversity-driven refinement approach to select the synthesized images that differ from known categories for subsequent OCD model training. Finally, we leverage a semi-supervised leader encoding to inject additional category knowledge contained in synthesized data into the OCD models, which can benefit the discovery of both known and unknown categories during the on-the-fly inference process. Extensive experiments demonstrate the superiority of our DiffGRE over previous methods on six fine-grained datasets.

cs.CV↗

arXiv2025

WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting

3D Gaussian Splatting (3DGS) has gained significant attention for 3D scene reconstruction, but still suffers from complex outdoor environments, especially under adverse weather. This is because 3DGS treats the artifacts caused by adverse weather as part of the scene and will directly reconstruct them, largely reducing the clarity of the reconstructed scene. To address this challenge, we propose WeatherGS, a 3DGS-based framework for reconstructing clear scenes from multi-view images under different weather conditions. Specifically, we explicitly categorize the multi-weather artifacts into the dense particles and lens occlusions that have very different characters, in which the former are caused by snowflakes and raindrops in the air, and the latter are raised by the precipitation on the camera lens. In light of this, we propose a dense-to-sparse preprocess strategy, which sequentially removes the dense particles by an Atmospheric Effect Filter (AEF) and then extracts the relatively sparse occlusion masks with a Lens Effect Detector (LED). Finally, we train a set of 3D Gaussians by the processed images and generated masks for excluding occluded areas, and accurately recover the underlying clear scene by Gaussian splatting. We conduct a diverse and challenging benchmark to facilitate the evaluation of 3D reconstruction under complex weather scenarios. Extensive experiments on this benchmark demonstrate that our WeatherGS consistently produces high-quality, clean scenes across various weather scenarios, outperforming existing state-of-the-art methods. See project page:https://jumponthemoon.github.io/weather-gs.

cs.CV↗

arXiv2024

WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation

In this work, we propose a novel approach, namely WeatherDG, that can generate realistic, weather-diverse, and driving-screen images based on the cooperation of two foundation models, i.e, Stable Diffusion (SD) and Large Language Model (LLM). Specifically, we first fine-tune the SD with source data, aligning the content and layout of generated samples with real-world driving scenarios. Then, we propose a procedural prompt generation method based on LLM, which can enrich scenario descriptions and help SD automatically generate more diverse, detailed images. In addition, we introduce a balanced generation strategy, which encourages the SD to generate high-quality objects of tailed classes under various weather conditions, such as riders and motorcycles. This segmentation-model-agnostic method can improve the generalization ability of existing models by additionally adapting them with the generated synthetic data. Experiments on three challenging datasets show that our method can significantly improve the segmentation performance of different state-of-the-art models on target domains. Notably, in the setting of ''Cityscapes to ACDC'', our method improves the baseline HRDA by 13.9% in mIoU.

cs.CV↗

arXiv2024

AllWeatherNet:Unified Image Enhancement for Autonomous Driving under Adverse Weather and Lowlight-conditions

Adverse conditions like snow, rain, nighttime, and fog, pose challenges for autonomous driving perception systems. Existing methods have limited effectiveness in improving essential computer vision tasks, such as semantic segmentation, and often focus on only one specific condition, such as removing rain or translating nighttime images into daytime ones. To address these limitations, we propose a method to improve the visual quality and clarity degraded by such adverse conditions. Our method, AllWeather-Net, utilizes a novel hierarchical architecture to enhance images across all adverse conditions. This architecture incorporates information at three semantic levels: scene, object, and texture, by discriminating patches at each level. Furthermore, we introduce a Scaled Illumination-aware Attention Mechanism (SIAM) that guides the learning towards road elements critical for autonomous driving perception. SIAM exhibits robustness, remaining unaffected by changes in weather conditions or environmental scenes. AllWeather-Net effectively transforms images into normal weather and daytime scenes, demonstrating superior image enhancement results and subsequently enhancing the performance of semantic segmentation, with up to a 5.3% improvement in mIoU in the trained domain. We also show our model's generalization ability by applying it to unseen domains without re-training, achieving up to 3.9% mIoU improvement. Code can be accessed at: https://github.com/Jumponthemoon/AllWeatherNet.

cs.CV↗

arXiv2024

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery

In this paper, we study a practical yet challenging task, On-the-fly Category Discovery (OCD), aiming to online discover the newly-coming stream data that belong to both known and unknown classes, by leveraging only known category knowledge contained in labeled data. Previous OCD methods employ the hash-based technique to represent old/new categories by hash codes for instance-wise inference. However, directly mapping features into low-dimensional hash space not only inevitably damages the ability to distinguish classes and but also causes "high sensitivity" issue, especially for fine-grained classes, leading to inferior performance. To address these issues, we propose a novel Prototypical Hash Encoding (PHE) framework consisting of Category-aware Prototype Generation (CPG) and Discriminative Category Encoding (DCE) to mitigate the sensitivity of hash code while preserving rich discriminative information contained in high-dimension feature space, in a two-stage projection fashion. CPG enables the model to fully capture the intra-category diversity by representing each category with multiple prototypes. DCE boosts the discrimination ability of hash code with the guidance of the generated category prototypes and the constraint of minimum separation distance. By jointly optimizing CPG and DCE, we demonstrate that these two components are mutually beneficial towards an effective OCD. Extensive experiments show the significant superiority of our PHE over previous methods, e.g., obtaining an improvement of +5.3% in ALL ACC averaged on all datasets. Moreover, due to the nature of the interpretable prototypes, we visually analyze the underlying mechanism of how PHE helps group certain samples into either known or unknown categories. Code is available at https://github.com/HaiyangZheng/PHE.

cs.CV↗

arXiv2024

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery

In this paper, we study the problem of Generalized Category Discovery (GCD), which aims to cluster unlabeled data from both known and unknown categories using the knowledge of labeled data from known categories. Current GCD methods rely on only visual cues, which however neglect the multi-modality perceptive nature of human cognitive processes in discovering novel visual categories. To address this, we propose a two-phase TextGCD framework to accomplish multi-modality GCD by exploiting powerful Visual-Language Models. TextGCD mainly includes a retrieval-based text generation (RTG) phase and a cross-modality co-teaching (CCT) phase. First, RTG constructs a visual lexicon using category tags from diverse datasets and attributes from Large Language Models, generating descriptive texts for images in a retrieval manner. Second, CCT leverages disparities between textual and visual modalities to foster mutual learning, thereby enhancing visual GCD. In addition, we design an adaptive class aligning strategy to ensure the alignment of category perceptions between modalities as well as a soft-voting mechanism to integrate multi-modality cues. Experiments on eight datasets show the large superiority of our approach over state-of-the-art methods. Notably, our approach outperforms the best competitor, by 7.7% and 10.8% in All accuracy on ImageNet-1k and CUB, respectively.

cs.CV↗

arXiv2024

Diffusion Models Meet Network Management: Improving Traffic Matrix Analysis with Diffusion-based Approach

Due to network operation and maintenance relying heavily on network traffic monitoring, traffic matrix analysis has been one of the most crucial issues for network management related tasks. However, it is challenging to reliably obtain the precise measurement in computer networks because of the high measurement cost, and the unavoidable transmission loss. Although some methods proposed in recent years allowed estimating network traffic from partial flow-level or link-level measurements, they often perform poorly for traffic matrix estimation nowadays. Despite strong assumptions like low-rank structure and the prior distribution, existing techniques are usually task-specific and tend to be significantly worse as modern network communication is extremely complicated and dynamic. To address the dilemma, this paper proposed a diffusion-based traffic matrix analysis framework named Diffusion-TM, which leverages problem-agnostic diffusion to notably elevate the estimation performance in both traffic distribution and accuracy. The novel framework not only takes advantage of the powerful generative ability of diffusion models to produce realistic network traffic, but also leverages the denoising process to unbiasedly estimate all end-to-end traffic in a plug-and-play manner under theoretical guarantee. Moreover, taking into account that compiling an intact traffic dataset is usually infeasible, we also propose a two-stage training scheme to make our framework be insensitive to missing values in the dataset. With extensive experiments with real-world datasets, we illustrate the effectiveness of Diffusion-TM on several tasks. Moreover, the results also demonstrate that our method can obtain promising results even with $5\%$ known values left in the datasets.

cs.NI↗

arXiv2024

Generative AI Enabled Matching for 6G Multiple Access

In wireless networks, applying deep learning models to solve matching problems between different entities has become a mainstream and effective approach. However, the complex network topology in 6G multiple access presents significant challenges for the real-time performance and stability of matching generation. Generative artificial intelligence (GenAI) has demonstrated strong capabilities in graph feature extraction, exploration, and generation, offering potential for graph-structured matching generation. In this paper, we propose a GenAI-enabled matching generation framework to support 6G multiple access. Specifically, we first summarize the classical matching theory, discuss common GenAI models and applications from the perspective of matching generation. Then, we propose a framework based on generative diffusion models (GDMs) that iteratively denoises toward reward maximization to generate a matching strategy that meets specific requirements. Experimental results show that, compared to decision-based AI approaches, our framework can generate more effective matching strategies based on given conditions and predefined rewards, helping to solve complex problems in 6G multiple access, such as task allocation.

cs.NI↗

arXiv2024

Revolutionizing Wireless Networks with Self-Supervised Learning: A Pathway to Intelligent Communications

With the rapid proliferation of mobile devices and data, next-generation wireless communication systems face stringent requirements for ultra-low latency, ultra-high reliability, and massive connectivity. Traditional AI-driven wireless network designs, while promising, often suffer from limitations such as dependency on labeled data and poor generalization. To address these challenges, we present an integration of self-supervised learning (SSL) into wireless networks. SSL leverages large volumes of unlabeled data to train models, enhancing scalability, adaptability, and generalization. This paper offers a comprehensive overview of SSL, categorizing its application scenarios in wireless network optimization and presenting a case study on its impact on semantic communication. Our findings highlight the potentials of SSL to significantly improve wireless network performance without extensive labeled data, paving the way for more intelligent and efficient communication systems.

eess.SP↗

arXiv2024

On solving a rank regularized minimization problem via equivalent factorized column-sparse regularized models

Rank regularized minimization problem is an ideal model for the low-rank matrix completion/recovery problem. The matrix factorization approach can transform the high-dimensional rank regularized problem to a low-dimensional factorized column-sparse regularized problem. The latter can greatly facilitate fast computations in applicable algorithms, but needs to overcome the simultaneous non-convexity of the loss and regularization functions. In this paper, we consider the factorized column-sparse regularized model. Firstly, we optimize this model with bound constraints, and establish a certain equivalence between the optimized factorization problem and rank regularized problem. Further, we strengthen the optimality condition for stationary points of the factorization problem and define the notion of strong stationary point. Moreover, we establish the equivalence between the factorization problem and its a nonconvex relaxation in the sense of global minimizers and strong stationary points. To solve the factorization problem, we design two types of algorithms and give an adaptive method to reduce their computation. The first algorithm is from the relaxation point of view and its iterates own some properties from global minimizers of the factorization problem after finite iterations. We give some analysis on the convergence of its iterates to the strong stationary point. The second algorithm is designed for directly solving the factorization problem. We improve the PALM algorithm introduced by Bolte et al. (Math Program Ser A 146:459-494, 2014) for the factorization problem and give its improved convergence results. Finally, we conduct numerical experiments to show the promising performance of the proposed model and algorithms for low-rank matrix completion.

math.OC↗

arXiv2024

Democratizing Fine-grained Visual Recognition with Large Language Models

Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average layperson does not excel at differentiating species of birds or mushrooms due to subtle differences among the species. A major bottleneck in developing FGVR systems is caused by the need of high-quality paired expert annotations. To circumvent the need of expert knowledge we propose Fine-grained Semantic Category Reasoning (FineR) that internally leverages the world knowledge of large language models (LLMs) as a proxy in order to reason about fine-grained category names. In detail, to bridge the modality gap between images and LLM, we extract part-level visual attributes from images as text and feed that information to a LLM. Based on the visual attributes and its internal world knowledge the LLM reasons about the subordinate-level category names. Our training-free FineR outperforms several state-of-the-art FGVR and language and vision assistant models and shows promise in working in the wild and in new domains where gathering expert annotation is arduous.

cs.CV↗

arXiv2024

MIFI: MultI-camera Feature Integration for Roust 3D Distracted Driver Activity Recognition

Distracted driver activity recognition plays a critical role in risk aversion-particularly beneficial in intelligent transportation systems. However, most existing methods make use of only the video from a single view and the difficulty-inconsistent issue is neglected. Different from them, in this work, we propose a novel MultI-camera Feature Integration (MIFI) approach for 3D distracted driver activity recognition by jointly modeling the data from different camera views and explicitly re-weighting examples based on their degree of difficulty. Our contributions are two-fold: (1) We propose a simple but effective multi-camera feature integration framework and provide three types of feature fusion techniques. (2) To address the difficulty-inconsistent problem in distracted driver activity recognition, a periodic learning method, named example re-weighting that can jointly learn the easy and hard samples, is presented. The experimental results on the 3MDAD dataset demonstrate that the proposed MIFI can consistently boost performance compared to single-view models.

cs.CV↗

arXiv2023

Learning to Generate Pseudo Personal Mobility

The importance of personal mobility data is widely recognized in various fields. However, the utilization of real personal mobility data raises privacy concerns. Therefore, it is crucial to generate pseudo personal mobility data that accurately reflects real-world mobility patterns while safeguarding user privacy. Nevertheless, existing methods for generating pseudo mobility data, such as mechanism-based and deep-learning-based approaches, have limitations in capturing sufficient individual heterogeneity. To address these gaps, taking pseudo-person(avatar) as ground-zero, a novel individual-based human mobility generator called GeoAvatar has been proposed - which considers individual heterogeneity in spatial and temporal decision-making, incorporates demographic characteristics, and provides interpretability. Our method utilizes a deep generative model to simulate heterogeneous individual life patterns, a reliable labeler for inferring individual demographic characteristics, and a Bayesian approach for generating spatial choices. Through our method, we have achieved the generation of heterogeneous individual human mobility data without accessing individual-level personal information, with good quality - we evaluated the proposed method based on physical features, activity patterns, and spatial-temporal characteristics, demonstrating its good performance, compared to mechanism-based modeling and black-box deep learning approaches. Furthermore, this method maintains extensibility for broader applications, making it a promising paradigm for generating human mobility data.

cs.CY↗

arXiv2023

CarDD: A New Dataset for Vision-based Car Damage Detection

Automatic car damage detection has attracted significant attention in the car insurance business. However, due to the lack of high-quality and publicly available datasets, we can hardly learn a feasible model for car damage detection. To this end, we contribute with Car Damage Detection (CarDD), the first public large-scale dataset designed for vision-based car damage detection and segmentation. Our CarDD contains 4,000 highresolution car damage images with over 9,000 well-annotated instances of six damage categories. We detail the image collection, selection, and annotation processes, and present a statistical dataset analysis. Furthermore, we conduct extensive experiments on CarDD with state-of-the-art deep methods for different tasks and provide comprehensive analyses to highlight the specialty of car damage detection. CarDD dataset and the source code are available at https://cardd-ustc.github.io.

cs.CV↗

arXiv2023

Prediction of nanobubble-assisted focused ultrasound-induced blood-brain barrier opening with machine learning

Novel approaches for predicting the outcomes of blood-brain barrier (BBB) opening with focused ultrasound (FUS) and microbubbles are highly desired. This study aims to explore machine learning-based methods for reliably predicting the FUS-induced BBB opening efficacy and safety. Methods: Sixteen female rats were used in this study. An acoustic feedback-controlled FUS system (f0: 0.5MHz) was used for the BBB opening with the infusion of custom-made nanobubbles/Definity. Evans Blue was injected for the BBB opening efficacy verification and the brain tissue was harvested for the safety assessment. Acoustic emissions were recorded, preprocessed and fed into three machine learning models for BBB opening outcomes prediction. Conventional stable and inertial cavitation dose were also calculated. Results: Among the tested machine learning models, a modified Support Vector Data Description (mSVDD) model achieved the best performance in the BBB opening efficacy and safety prediction with an accuracy of 85.0+/-16.6% and 62.5+/-12.8%, respectively. Conventional stable and inertial cavitation dose-based prediction has a prediction accuracy of 80.0% in efficacy and 34.3% in safety, respectively. The mSVDD model trained with the overall bubble response (0-2 MHz) performed better than that trained with the ultra-harmonic bubble response (0.7-0.8 MHz) in both efficacy prediction (85.0+/-16.6% vs 76.0+/-8.0%, p=0.04) and safety prediction (62.5+/-12.8% vs 55.0+/-10.7%, p>0.05). It is also found that the mSVDD model trained with nanobubble data cannot be directly applied to Definity. Conclusion: Our investigations demonstrated that it is feasible to achieve a reliable prediction of FUS-induced BBB opening outcomes with machine learning and acoustic signals from stimulated nanobubbles. This study provided a new approach for the prediction of FUS-BBB opening outcomes with a clinical translation potential.

physics.med-ph↗

arXiv2022

DC algorithms for a class of sparse group $\ell_0$ regularized optimization problems

In this paper, we consider a class of sparse group $\ell_0$ regularized optimization problems. Firstly, we give a continuous relaxation model of the considered problem and establish the equivalence of these two problems in the sense of global minimizers. Then, we define a class of stationary points of the relaxation problem, and prove that any defined stationary point is a local minimizer of the considered sparse group $\ell_0$ regularized problem and satisfies a desirable property of its global minimizers. Further, based on the difference-of-convex (DC) structure of the relaxation problem, we design two DC algorithms to solve the relaxation problem. We prove that any accumulation point of the iterates generated by them is a stationary point of the relaxation problem. In particular, all accumulation points have a common support set and a unified lower bound for the nonzero entries, and their zero entries can be attained within finite iterations. Moreover, we prove the convergence of the entire iterates generated by the proposed algorithms. Finally, we give some numerical experiments to show the efficiency of the proposed algorithms.

math.OC↗

arXiv2021

Field-Free Deterministic Writing of SOT-MTJ by Unipolar Current

We propose a manufacturable solution for field-free writing of perpendicular SOT-MTJ without sacrificing integration density on a 200 mm wafer. The field-free writing operation can be achieved by unipolar current pulses via engineering the interlayer exchange coupling in SOT-MTJ thin films. The proposed device can reach a high writing speed of up to 1 ns and work properly at temperature of 100 C. The deterministic writing of SOT-MTJ by unipolar current offers an effective approach for high density SOT-MRAM integration.

cond-mat.mes-hall↗

arXiv2021

Mobsimilarity: Vector Graph Optimization for Mobility Tableau Comparison

Human mobility similarity comparison plays a critical role in mobility estimation/prediction model evaluation, mobility clustering and mobility matching, which exerts an enormous impact on improving urban mobility, accessibility, and reliability. By expanding origin-destination matrix, we propose a concept named mobility tableau, which is an aggregated tableau representation to the population flow distributed between different location pairs of a study site and can be represented by a vector graph. Compared with traditional OD matrix-based mobility comparison, mobility tableau comparison provides high-dimensional similarity information, including volume similarity, spatial similarity, mass inclusiveness and structure similarity. A novel mobility tableaus similarity measurement method is proposed by optimizing the least spatial cost of transforming the vector graph for one mobility tableau into the other and is optimized to be efficient. The robustness of the measure is supported through several sensitive analysis on GPS based mobility tableau. The better performance of the approach compared with traditional mobility comparison methods in two case studies demonstrate the practicality and superiority, while one study is estimated mobility tableaus validation and the other is different cities' mobility tableaus comparison.

cs.CY↗