Subspace-based DPSGD has emerged as a robust solution for alleviating excessive noise in high-dimensional, privacy-preserving visual learning. It achieves a favorable privacy-utility balance by projecting privatized gradients onto a low-rank subspace derived from in-distribution public data. However, relying solely on limited public data can narrow the diversity of the anchored subspace and induce over-memorization into model training, leading to suboptimal private optimization.To overcome these limitations, we propose a synthesis-augmented subspace-based DPSGD framework, SAS-DPSGD, which integrates synthetic data into the subspace construction process. We quantitatively analyze the private optimization performance using the subspace derived from the mixed public and synthetic data, revealing the benefits as well as the saturation effects of incorporating synthetic data in private visual learning. To the best of our knowledge, this is the first work to provide a unified theoretical guarantee to synthesis-augmented subspace-based DPSGD. Moreover, we design an early projection mechanism within our framework that projects the gradient onto the subspace before performing gradient clipping. This mechanism effectively reduces the gradient clipping bias and lowers the synthetic data requirement, resulting in a faster convergence rate. Extensive experiments on two real-world datasets validate that SAS-DPSGD outperforms nine baselines by up to 9.78% in accuracy and can reduce the amount of synthetic data required by 66.7%.
论文检索
输入标题、作者或关键词，从 3,655 篇学术成果中精准定位
The detection and grounding of manipulated content in multimodal data has emerged as a critical challenge in media forensics. While existing benchmarks demonstrate technical progress, they suffer from misalignment artifacts that poorly reflect real-world manipulation patterns: practical attacks typically maintain semantic consistency across modalities, whereas current datasets artificially disrupt cross-modal alignment, creating easily detectable anomalies. To bridge this gap, we pioneer the detection of semantically-coordinated manipulations where visual edits are systematically paired with semantically consistent textual descriptions. Our approach begins with constructing the first Semantic-Aligned Multimodal Manipulation (SAMM) dataset, generated through a two-stage pipeline: 1) applying state-of-the-art image manipulations, followed by 2) generation of contextually-plausible textual narratives that reinforce the visual deception. Building on this foundation, we propose a Retrieval-Augmented Manipulation Detection and Grounding (RamDG) framework. RamDG commences by harnessing external knowledge repositories to retrieve contextual evidence, which serves as the auxiliary texts and encoded together with the inputs through our image forgery grounding and deep manipulation detection modules to trace all manipulations. Extensive experiments demonstrate our framework significantly outperforms existing methods, achieving 2.06% higher detection accuracy on SAMM compared to state-of-the-art approaches. The dataset and code are publicly available at https://github.com/shen8424/SAMM-RamDG-CAP.
Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples significantly limits the effectiveness of existing methods in tasks such as localization and classification. While several anomaly synthesis approaches have been introduced for data augmentation, they often struggle with low realism, inaccurate mask alignment, and poor generalization. To overcome these limitations, we propose Generate Aligned Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework. GAA leverages the strong priors of a pretrained latent diffusion model to generate realistic, diverse, and semantically aligned anomalies using only a small number of samples. The framework first employs Localized Concept Decomposition to jointly model the semantic features and spatial information of anomalies, enabling flexible control over the type and location of anomalies. It then utilizes Adaptive Multi-Round Anomaly Clustering to perform fine-grained semantic clustering of anomaly concepts, thereby enhancing the consistency of anomaly representations. Subsequently, a region-guided mask generation strategy ensures precise alignment between anomalies and their corresponding masks, while a low-quality sample filtering module is introduced to further improve the overall quality of the generated samples. Extensive experiments on the MVTec AD and LOCO datasets demonstrate that GAA achieves superior performance in both anomaly synthesis quality and downstream tasks such as localization and classification.
In this work, we study how vision-language models (VLMs) can be utilized to enhance the safety for the autonomous driving system, including perception, situational understanding, and path planning. However, existing research has largely overlooked the evaluation of these models in traffic safety-critical driving scenarios. To bridge this gap, we create the benchmark (SafeDrive228K) and propose a new baseline based on VLM with knowledge graph-based retrieval-augmented generation (SafeDriveRAG) for visual question answering (VQA). Specifically, we introduce SafeDrive228K, the first large-scale multimodal question-answering benchmark comprising 228K examples across 18 sub-tasks. This benchmark encompasses a diverse range of traffic safety queries, from traffic accidents and corner cases to common safety knowledge, enabling a thorough assessment of the comprehension and reasoning abilities of the models. Furthermore, we propose a plug-and-play multimodal knowledge graph-based retrieval-augmented generation approach that employs a novel multi-scale subgraph retrieval algorithm for efficient information retrieval. By incorporating traffic safety guidelines collected from the Internet, this framework further enhances the model's capacity to handle safety-critical situations. Finally, we conduct comprehensive evaluations on five mainstream VLMs to assess their reliability in safety-sensitive driving tasks. Experimental results demonstrate that integrating RAG significantly improves performance, achieving a +4.73% gain in Traffic Accidents tasks, +8.79% in Corner Cases tasks and +14.57% in Traffic Safety Commonsense across five mainstream VLMs, underscoring the potential of our proposed benchmark and methodology for advancing research in traffic safety. Our source code and data are available at https://github.com/Lumos0507/SafeDriveRAG.
Cloth-changing Person Re-Identification (CCReID) aims to recognize individuals across clothing variations by learning clothing-invariant representations. However, obtaining sufficient samples of the same person in diverse outfits is often impractical. While synthesizing realistic person images provides an effective solution, existing augmentation methods require labeled data and external priors (e.g., pose skeletons, semantic maps), resulting in high costs and limited generalization. To this end, we propose a Prior-Free Augmentation method for Cloth-changing person re-identification (PFAC), which leverages text guidance to synthesize images with clothing variations while maintaining identity consistency. Our approach features: (1) a truncated diffusion model that preserves clothing-invariant structural cues from intermediate noisy images, (2) a dual-branch denoising network that decouples text-guided clothing synthesis from identity consistency via cross-modal alignment, and (3) a joint optimization strategy with identity-focused losses and image filtering to enhance realism and discriminability. Experimental results on PRCC, LTCC, and Celeb-reID datasets demonstrate that PFAC achieves state-of-the-art CCReID performance, effectively generating high-fidelity, identity-consistent images for robust augmentation without external priors.
Monocular texture 3D human reconstruction aims to create a complete 3D digital avatar from just a single front-view human RGB image. However, the geometric ambiguity inherent in a single 2D image and the scarcity of 3D human training data are the main obstacles limiting progress in this field. To address these issues, current methods employ prior geometric estimation networks to derive various human geometric forms, such as the SMPL model and normal maps. However, they struggle to integrate these modalities effectively, leading to view inconsistencies, such as facial distortions. To this end, we propose a two-process 3D human reconstruction framework, SAT, which seamlessly learns various prior geometries in a unified manner and reconstructs high-quality textured 3D avatars as the final output. To further facilitate geometry learning, we introduce a Supervisor Feature Regularization module. By employing a multi-view network with the same structure to provide intermediate features as training supervision, these varied geometric priors can be better fused. To tackle data scarcity and further improve reconstruction quality, we also propose an Online Animation Augmentation module. By building a one-feed-forward animation network, we augment a massive number of samples from the original 3D human data online for model training. Extensive experiments on two benchmarks show the superiority of our approach compared to state-of-the-art methods.
360° omnidirectional images (ODIs) have gained considerable attention recently, and are widely used in various virtual reality (VR) and augmented reality (AR) applications. However, capturing such images is expensive and requires specialized equipment, making ODI synthesis increasingly important. While common 2D image generation and editing methods are rapidly advancing, these models struggle to deliver satisfactory results when generating or editing ODIs due to the unique format and broad 360° Field-of-View (FoV) of ODIs. To bridge this gap, we construct Any2Omni , the first comprehensive ODI generation-editing dataset comprises 60,000+ training data covering diverse input conditions and up to 9 ODI generation and editing tasks. Built upon Any2Omni, we propose an Omni model for Omni-directional image generation and editing ( Omni 2), with the capability of handling various ODI generation and editing tasks under diverse input conditions using one model. Extensive experiments demonstrate the superiority and effectiveness of the proposed Omni2 model for both the ODI generation and editing tasks. Both the Any2Omni dataset and the Omni2 model are publicly available at: https://github.com/IntMeGroup/Omni2.
The performance of computer vision models in certain real-world applications, such as medical diagnosis, is often limited by the scarcity of available images. Expanding datasets using pre-trained generative models is an effective solution. However, due to the uncontrollable generation process and the ambiguity of natural language, noisy images may be generated. Re-weighting is an effective way to address this issue by assigning low weights to such noisy images. We first theoretically analyze three types of supervision for the generated images. Based on the theoretical analysis, we develop TriReWeight, a triplet-connection-based sample re-weighting method to enhance generative data augmentation. Theoretically, TriReWeight can be integrated with any generative data augmentation methods and never downgrade their performance. Moreover, its generalization approaches the optimal in the order O(√d ln (n)/n). Our experiments validate the correctness of the theoretical analysis and demonstrate that our method outperforms the existing SOTA methods by 7.9% on average over six natural image datasets and by 3.4% on average over three medical datasets. We also experimentally validate that our method can enhance the performance of different generative data augmentation methods.
Text-to-audio (T2A) generation has achieved promising results with the recent advances in generative models. However, because of the limited quality and quantity of temporally-aligned audio-text pairs, existing T2A methods struggle to handle the complex text prompts that contain precise timing control, e.g., owl hooted at 2.4s-5.2s. Recent works have explored data augmentation techniques or introduced timing conditions as model inputs to enable timing-conditioned 10-second T2A generation, while their synthesis quality is still limited. In this work, we propose a novel training-free timing-controlled T2A framework, FreeAudio, making the first attempt to enable timing-controlled long-form T2A generation, e.g., owl hooted at 2.4s-5.2s and crickets chirping at 0s-24s. Specifically, we first employ an LLM to plan non-overlapping time windows and recaption each with a refined natural language description, based on the input text and timing prompts. Then we introduce: 1) Decoupling & Aggregating Attention Control for precise timing control; 2) Contextual Latent Composition for local smoothness and Reference Guidance for global consistency. Extensive experiments show that: 1) FreeAudio achieves state-of-the-art timing-conditioned T2A synthesis quality among training-free methods and is comparable to leading training-based methods; 2) FreeAudio demonstrates comparable long-form generation quality with training-based Stable Audio and paves the way for timing-controlled long-form T2A synthesis. Demo samples are available at: https://freeaudio.github.io/FreeAudio/.
Scalable Vector Graphics (SVG) has become an indispensable technology in front-end development and UI/UX design, due to its inherent advantages in scalability, editability, and rendering efficiency. In the creation of vector graphics, while expressing creative concepts is straightforward, translating them into precise digital artworks is often challenging and time-consuming. To overcome this technical bottleneck and achieve intelligent conversion from concept to final product, we have constructed SVG-1M, a large-scale dataset of high-quality SVG samples with paired textual descriptions. Through innovative data augmentation and annotation processes, we built precisely aligned ''Text instruction-SVG code'' training pairs, with a subset enhanced by Chain-of-Thought (CoT) annotations. This provides rich semantic supervision signals for model learning. Based on this dataset, we propose SVGen, an end-to-end generative model capable of directly converting natural language descriptions into SVG code. This design addresses the challenges of generating semantically accurate vector graphics while preserving complete structural information. We explored various training strategies and introduced a progressive curriculum learning approach, optimized with reinforcement learning algorithms. Notably, this study innovatively applies the CoT paradigm to vector graphics generation, effectively enhancing both the accuracy and interpretability of SVG synthesis. Experimental validation demonstrates that SVGen exhibits significant advantages over general large models in terms of SVG generation quality, while also surpassing optimization-based rendering methods in generation efficiency. The proposed method enables intelligent conversion between natural language and vector graphics, enabling novel workflows like real-time AI-assisted design iteration. Code, model, and data is released at: https://github.com/gitcat-404/SVGen
Medical time series, such as Electroencephalogram (EEG) and Electrocardiogram (ECG), are widely used for disease detection, with multiple electrodes or sensors recording simultaneously. Accurately modeling inter-channel relationships is crucial for improving detection performance. Current methods mainly rely on data-driven approaches to model channel relationships, facing two challenges: (1) insufficient integration of medical prior knowledge, hindering the accurate representation of physiological correlations between channels, and (2) high temporal pattern similarity across channels, leading to feature redundancy and degraded classification performance. To address these issues, we introduce KEMed, a knowledge-augmented model for medical time series classification. The model incorporates medical textual prior knowledge by generating natural language descriptions for each channel and leveraging Pre-trained Language Model (PLM) for semantic representation, enabling precise identification of physiological and pathological similarities and differences between channels. Specifically, KEMed optimizes channel relationships through knowledge-guided clustering and weighting mechanisms and leverages Large Language Model (LLM) to capture spatiotemporal dependencies, thereby enhancing classification performance. Experimental results on five medical time series datasets demonstrate that KEMed consistently outperforms state-of-the-art methods, validating the effectiveness and superiority of knowledge augmentation in medical time series classification.
The pelvis is a high-incidence region for trauma, and its precise segmentation is vital for clinical diagnosis and treatment. Although deep learning has achieved high precision for pelvis segmentation, it is still confronted with challenges such as the scarcity of medical data and the high cost of annotation. Recently, generative models have offered a viable solution through synthetic data augmentation. Thus, we propose a novel text-conditioned generative framework that simultaneously produces high-fidelity CT images and their corresponding segmentation masks, with a special focus on accurately generating symmetric pelvic structures, including the left hip bone, right hip bone and sacrum. Firstly, we fine-tuned a medical text encoder to transform detailed descriptions into precise generation conditions. Considering the easily overlooked symmetry attribute in pelvic bone images, we introduced a novel coordinate-aware enhancement module that incorporates bone-specific centroid coordinates for symmetrical awareness. Finally, we expanded it to multi-task learning for generation of paired pelvic images and segmentation labels. To test our method, we released a pelvic CT image dataset with textual description (CT-PelvisText) and then transferred it to downstream segmentation using the generative pelvic image. Our experiments demonstrate the reliability of our method, which contributes to accurate pelvic segmentation. This work can also be easily extended to other medical images with symmetry properties, which provides potential for efficient learning in small-sample datasets. Our code and dataset are available at: https://github.com/CurellaSong/TSA_LDM.
Cross-Domain Few-Shot Learning (CD-FSL) aims to transfer knowledge acquired from a source domain with abundant data to the target domain with limited labeled samples. Recent advancements have enhanced model generalization through Perturbation Augmentation (PA), facilitating more effective knowledge transfer. However, PA-based CD-FSL methods still suffer from two critical challenges, i.e., (1) limited diversity of augmented samples, making it difficult to cover the true distribution of unseen domains, and (2) conflicting gradients during model optimization, where augmented and original samples drive the model's optimization in opposing directions. To address these issues, we propose a novel PA-based framework with Style-Decoupled Augmentation (SDA) and Gradient-Conflict Adjustment (GCA) for Cross-Domain Few-Shot Learning, which is termed ''SG-FSL''. Specifically, SDA decouples the source domain style into style weights and basis styles, generating diverse unseen styles by perturbing the style weights to reweight the basis styles. Meanwhile, GCA leverages the angular relationships between the domain-specific gradient directions of augmented and original features, adaptively adjusting the gradient directions of original features to ensure that the model acquires diverse domain knowledge without interference, guiding it toward conflict-free optimization. Comprehensive experiments on multiple benchmark datasets consistently demonstrate the effectiveness and superiority of our method over state-of-the-art baselines.
3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation. However, most augmentation strategies only focus on local transformations or semantic recomposition, lacking the consideration of global structural dependencies within scenes. To address this limitation, we propose a graph-guided data augmentation framework with dual-level constraints for realistic 3D scene synthesis. Our method learns object relationship statistics from real-world data to construct guiding graphs for scene generation. Local-level constraints enforce geometric plausibility and semantic consistency between objects, while global-level constraints maintain the topological structure of the scene by aligning the generated layout with the guiding graph. Extensive experiments on indoor and outdoor datasets demonstrate that our framework generates diverse and high-quality augmented scenes, leading to consistent improvements in point cloud segmentation performance across various models. Code is available at: https://github.com/alexander7xu/DualLevelAug
Early screening for Alzheimer's Disease (AD) through speech presents a promising non-invasive approach. However, challenges such as limited data and the lack of fine-grained, adaptive feature selection often hinder performance. To address these issues, we propose MoTAS, a robust framework designed to enhance AD screening efficiency. MoTAS leverages Text-to-Speech (TTS) augmentation to increase data volume and employs a Mixture of Experts (MoE) mechanism to improve multimodal feature selection, jointly enhancing model generalization. The process begins with automatic speech recognition (ASR) to obtain accurate transcriptions. TTS is then used to synthesize speech that enriches the dataset. After extracting acoustic and text embeddings, the MoE mechanism dynamically selects the most informative features, optimizing feature fusion for improved classification. Evaluated on the ADReSSo dataset, MoTAS achieves a leading accuracy of 85.71%, outperforming existing baselines. Ablation studies further validate the individual contributions of TTS augmentation and MoE in boosting classification performance. These findings highlight the practical value of MoTAS in real-world AD screening scenarios, particularly in data-limited settings.
Single-source domain generalization (SDG) in medical image segmentation is a challenging yet practical task that efficiently enhances generalization ability while avoiding high annotation costs and privacy concerns. In this paper, we propose EIR-SDG, a novel SDG approach that explores domain-invariant representation for medical image segmentation. The core of EIR-SDG lies in mitigating the effect of style in the encoder while facilitating robust segmentation in the decoder. Concretely, we design a training-free texture and style diversity module that transforms images into diverse random appearances without requiring optimization or gradient updates, which simulates unseen target distributions while mitigating overfitting to regular patterns in synthetic data. Building on this, we devise a feature adaptive whitening module, which disentangles and whitens the style-sensitive feature correlations between original and augmented pairs, encouraging the encoder to learn invariant representations. Moreover, to facilitate robust segmentation in the decoder, a semantic representation optimization strategy is devised to enhance invariant representations by constraining the correlation between class prototypes to be consistent while improving segmentation boundary distinction by separating different class prototypes. Experiments on cross-modality abdominal, cross-sequence cardiac and cross-center prostate segmentation tasks demonstrate that our method achieves promising generalization capacity and outperforms the SOTA methods.
Unified Anomaly Detection (UAD) aims to identify anomalies across diverse domains without access to target domain data during training. Unlike traditional anomaly detection methods that rely on training separate models for each domain, UAD employs a single model to generalize across multiple categories. A key challenge lies in the domain shift between seen and unseen data, which requires capturing invariant discriminative patterns between reference and query images across different domains during in-context learning for unified anomaly detection. To tackle this, we propose a novel UAD framework to learn the invariant discriminative patterns through pre-, in- and post-processing modules. First, a pre-processing VLM-guided data augmentation module generates diverse and semantically consist images, followed by a latent-space filtering mechanism. Second, an in-processing Adaptive VQ memory module stores representative discriminative patterns to enable robust residual comparison. Third, a post-processing GUR (Geometric distributions Upgrade Representation) feature augmentation module models geometric feature distributions to synthesize informative prompts, improving the quality of feature delta estimation for anomaly scoring. Extensive experiments on benchmark datasets demonstrate that our method achieves superior generalization in detecting anomalies across unseen domains, outperforming existing state-of-the-art approaches.
The oracle bone inscription (OBI) recognition plays a significant role in understanding the history and culture of ancient China. However, the existing OBI datasets suffer from a long-tail distribution problem, leading to biased performance of OBI recognition models across majority and minority classes. With recent advancements in generative models, OBI synthesis-based data augmentation has become a promising avenue to expand the sample size of minority classes. Unfortunately, current OBI datasets lack large-scale structure-aligned image pairs for generative model training. To address these problems, we first present the Oracle-P15K, a structure-aligned OBI dataset for OBI generation and denoising, consisting of 14,542 images infused with domain knowledge from OBI experts. Second, we propose a diffusion model-based pseudo OBI generator, called OBIDiff, to achieve realistic and controllable OBI generation. Given a clean glyph image and a target rubbing-style image, it can effectively transfer the noise style of the original rubbing to the glyph image. Extensive experiments on OBI downstream tasks and user preference studies show the effectiveness of the proposed Oracle-P15K dataset and demonstrate that OBIDiff can accurately preserve inherent glyph structures while transferring authentic rubbing styles effectively. The dataset, code, and pre-trained models are available at https://github.com/LJHolyGround/Oracle-P15K.
The proliferation of satellite-related commonsense data on the internet. Traditional analytical methods are challenging to integrate and effectively uncover implicit knowledge within them. However, current deep learning and LLM-based approaches often struggle with errors and hallucinations when performing multi-hop reasoning in domain-specific contexts. To address these limitations, we propose a novel multi-hop reasoning framework for implicit commonsense mining. This framework aims to uncover the underlying meta-knowledge behind reasoning problems, thereby providing enhanced interpretability of the reasoning process. Specifically, we design an extraction-retrieval-principle multi-step reasoning method that generates different levels of meta-knowledge in stages to support the reasoning process effectively. We further design the mixture of expert knowledge graph construction to construct a satellite knowledge graph that supports multi-hop reasoning. Experimental results demonstrate that our approach outperforms baselines on satellite knowledge graph reasoning.
Binaural audio generation (BAG) aims to convert monaural audio to stereo audio using visual prompts, requiring a deep understanding of spatial and semantic information. The success of the BAG systems depends on the effectiveness of cross-modal reasoning and spatial understanding. Current methods have explored the use of visual information as guidance for binaural audio generation. However, they rely solely on cross-attention mechanisms to guide the generation process and under-utilise the temporal and spatial information in video data during training and inference. These limitations result in the loss of fine-grained spatial details and risk overfitting to specific environments, ultimately constraining model performance. In this paper, we address the aforementioned issues by introducing a new audio-visual binaural generation model with an audio-visual conditional normalisation layer that dynamically aligns the target difference audio features using visual context. To enhance spatial sensitivity, we also introduce a contrastive learning method that mines negatives from shuffled visual features. We also introduce a cost-efficient way to utilise test-time augmentation in video data to enhance performance. Our approach achieves state-of-the-art generation accuracy on the FAIR-Play, MUSIC-Stereo, and YT-MUSIC benchmarks. Code is available at https://github.com/SonyResearch/CCStereo.