Pre-trained Vision-Language Models (VLMs), e.g. CLIP, have become essential tools in multimodal transfer learning. However, fine-tuning VLMs in few-shot scenarios poses significant challenges in balancing task-specific adaptation and generalization in the obtained model. Meanwhile, current researches have predominantly focused on prompt-based adaptation methods, leaving adapter-based approaches underexplored and revealing notable performance gaps. To address these challenges, we introduce a novel Reconstruction-based Multimodal Adapter (RMAdapter), which leverages a dual-branch architecture. Unlike conventional single-branch adapters, RMAdapter consists of: (1) an adaptation branch that injects task-specific knowledge through parameter-efficient fine-tuning, and (2) a reconstruction branch that preserves general knowledge by reconstructing latent space features back into the original feature space. This design facilitates a dynamic balance between general and task-specific knowledge. Importantly, although RMAdapter introduces an additional reconstruction branch, it is carefully optimized to remain lightweight. By computing reconstruction loss locally at each layer and sharing projection modules, the overall computational overhead is kept minimal. A consistency constraint is also incorporated to better regulate the trade-off between discriminability and generalization. We comprehensively evaluate the effectiveness of RMAdapter on three representative tasks: generalization to new categories, generalization to new target datasets, and domain generalization. Without relying on data augmentation or duplicate prompt designs, our RMAdapter consistently outperforms state-of-the-art approaches across all evaluation metrics.
论文检索
输入标题、作者或关键词，从 801 篇学术成果中精准定位
Dynamic Semantic Tokenization for Time Series via Elastic Sampling on Physics-aware Perception
PDF ↗Despite the remarkable success of semantic token learning in NLP and vision domains, token-level representation mechanisms face fundamental challenges when extended to continuous time series analysis. We identify a core limitation lies in the intrinsic absence of semantically meaningful tokenization boundaries within time-series, which differs substantially from discrete text tokens and presents unique complexities compared to spatially coherent image patches. While existing works mechanically apply fixed-length partitioning, recent evidence from time series foundation models reveals performance ceilings in prediction tasks under such paradigms. This paper introduces a novel tokenization framework known as physics-aware tokenization (PATK), designed to implement adaptive time-frequency tokenization via distribution-sensitive sampling strategies. Key innovations include: 1) A Rate-of-Variation (RoV) distribution is meticulously structured to encompass multi-scale temporal dynamics in the time domain, alongside a Spectral Energy Intensity (SEI) distribution devised to reveal global seasonal patterns within the frequency domain; 2) A physics-aware hidden Markov modeling (PA-HMM) is then established to adaptively breaks down continuous time-series into distinct tokens with elastic lengths, responding to physics-aware probabilities sampled from RoV and SEI distributions. The proposed PATK allows steady integration with both conventional Transformers and advanced large-scale time series models (including LLM-transferred methods and pretrained time series foundation models). Simulations across various datasets demonstrate that PATK excels in classification and forecasting tasks, showing notable adaptability to model long-term dependencies, strengthening resilience against disturbances, and robustness to missing data events.
Recent advances in parameter-efficient transfer learning have demonstrated the utility of composing LoRA adapters from libraries of pretrained modules. However, most existing approaches rely on simple retrieval heuristics or uniform averaging, which overlook the latent structure of task relationships in representation space. We propose a new framework for adapter reuse that moves beyond retrieval, formulating adapter composition as a geometry-aware sparse reconstruction problem. Specifically, we represent each task by a latent prototype vector derived from the base model’s encoder and aim to approximate the target task prototype as a sparse linear combination of retrieved reference prototypes, under an L1-regularized optimization objective. The resulting combination weights are then used to blend the corresponding LoRA adapters, yielding a composite adapter tailored to the target task. This formulation not only preserves the local geometric structure of the task representation manifold, but also promotes interpretability and efficient reuse by selecting a minimal set of relevant adapters. We demonstrate the effectiveness of our approach across multiple domains—including medical image segmentation, medical report generation and image synthesis. Our results highlight the benefit of coupling retrieval with latent geometry-aware optimization for improved zero-shot generalization.
Diffusion models have achieved impressive generative performance across diverse domains such as image, video, and scientific data generation. However, fine-tuning these models for new tasks remains challenging due to their large scale, architectural diversity, and high sensitivity to hyperparameters—particularly learning rates. In this work, we propose Wasserstein-Aware Transfer (WAT), a principled and effective fine-tuning strategy grounded in diffusion trajectory analysis and optimal transport theory. Our key insight is that the distributional discrepancies between diffusion trajectories from different datasets decrease progressively over time and converge near the noise end. Based on this observation, we introduce a class-wise matching mechanism that minimizes the Wasserstein distance between class distributions of source and target datasets. This enables alignment at the class level without modifying the standard fine-tuning pipeline. To further enhance knowledge retention, we propose a novel sampling strategy that linearly combines class-conditional outputs from both pretrained and fine-tuned models. This method is simple yet effective, requiring negligible computational overhead while preserving domain-specific and generalizable knowledge. Extensive experiments across seven diverse benchmarks demonstrate that WAT reliably enhances generation quality under distribution shifts, outperforming competitive baselines. These results underscore its robustness and affirm the potential of optimal transport as a principled basis for knowledge transfer in diffusion models.
Domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, enabling effective retrieval while mitigating domain discrepancies. However, existing methods encounter several fundamental limitations: 1) neglecting class-level semantic alignment and excessively pursuing pair-wise sample alignment; 2) lacking either pseudo-label reliability consideration or geometric guidance for assessing label correctness; 3) directly quantizing original features affected by domain shift, undermining the quality of learned hash codes. In view of these limitations, we propose Prototype-based Semantic Consistency Alignment (PSCA), a two-stage framework for effective domain adaptive retrieval. In the first stage, a set of orthogonal prototypes directly establishes class-level semantic connections, maximizing inter-class separability while gathering intra-class samples. During the prototype learning, geometric proximity provides a reliability indicator for semantic consistency alignment through adaptive weighting of pseudo-label confidences. The resulting membership matrix and prototypes facilitate feature reconstruction, ensuring quantization on reconstructed rather than original features, thereby improving subsequent hash coding quality and seamlessly connecting both stages. In the second stage, domain-specific quantization functions process the reconstructed features under mutual approximation constraints, generating unified binary hash codes across domains. Extensive experiments validate PSCA's superior performance across multiple datasets.
Modern AI services must continually adapt to newly joined domains, yet delivering high-quality customized models is hampered by label sparsity, domain shifts, and tight budgets. We formulate this challenge as the learning system expansion problem and introduce HaT, an efficient heterogeneity-aware knowledge-transfer framework. HaT first selects a small set of high-quality source models with minimal overhead, and then fuses their imperfect predictions through a sample-wise attention mixer. Later, it adaptively distills the fused knowledge into target models via a knowledge dictionary. Extensive experiments on different tasks and modalities show that HaT outperforms state-of-the-art baselines by up to 16.5% accuracy, and saves 31.1% training time and up to 93.0% traffic.
Few-shot image classification (FSIC) aims to recognize novel categories from only a few labeled examples, making it inherently challenging under limited supervision. Existing approaches have attempted to alleviate this issue by incorporating explicit semantics like class names or knowledge graphs to guide learning. However, such methods often encounter semantic ambiguity due to their dependence on either overly simplistic semantic priors or resource-intensive external knowledge sources, which limits their potential. In this paper, we explore the frequency domain as an implicit and task-adaptive source of semantic information. We propose F2SST, a Frequency-to-Spatial Semantic Transfer framework that enhances feature learning by leveraging spectral signals as hidden semantics. Specifically, F2SST applies Fast Fourier Transform (FFT) to extract phase-invariant global frequency descriptors, followed by a lightweight Gated Spectral Attention (GSA) module that selectively emphasizes class-relevant frequency components. These enhanced spectral cues are then integrated into the spatial stream through a class-guided fusion mechanism, enabling more robust and semantically aligned representations. Extensive experiments on four standard benchmarks (miniImageNet, tieredImageNet, CIFAR-FS and FC100) demonstrate that F2SST consistently improves performance, validating the effectiveness of frequency-domain semantics in FSIC.
GCA: Geometry-aware Conditional Alignment for Partial Domain Adaptation with Coding Rate Reduction
PDF ↗Partial Domain Adaptation (PDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, where the target label space is a subset of the source label space. In PDA scenario, existing methods typically achieve transferability through distribution alignment in a statistical framework, and discriminability through geometric modeling. These two aspects are often treated as separate frameworks, which severs the intrinsic connection between them. To bridge this gap, we propose a unified framework termed Geometry-aware Conditional Alignment (GCA), which is derived from theoretical insights of Maximum Coding Rate Reduction. GCA collaboratively achieves conditional alignment and orthogonal discriminability in a unified framework, making the learned features more interpretable in both statistical and geometric aspects. As a result, GCA effectively enhances both the transferability and discriminability of features. Extensive experiments on four benchmark datasets validate the effectiveness of GCA.
Multi-Level Domain Adaptation and Contrastive Domain Isolation with Bilinear Fusion for Patient Drug Response Prediction
PDF ↗Accurate prediction of patient drug response is critical for precision cancer medicine but remains constrained by limited clinical data. While in vitro cell line data offer a scalable alternative, effective cross-domain transfer remains challenging. Many existing methods tend to overlook heterogeneous domain shifts across biological contexts, underrepresent the intrinsic differences between cell lines and patient tissues, and insufficiently capture high-order gene-drug interactions. To address these challenges, we propose MACB-DRP, a hierarchical transfer learning framework comprising three complementary stages that progressively coordinate adaptation across tissue, drug, and sample levels while enabling representation separation. The framework begins with tissue-aware domain adaptation, leveraging cancer-type classification and unsupervised alignment to preserve biologically meaningful structure across domains. It then incorporates drug-conditioned adversarial transfer for distribution alignment, coupled with bilinear fusion to model nonlinear and high-order gene-drug interactions. Finally, contrastive anchoring with feature-matched pairs enables fine-grained sample-level alignment, while feature-mismatched negatives preserve irreducible biological disparities. Experimental evaluation demonstrates that MACB-DRP achieves comprehensive predictive performance for patient drug responses, with robust results across multiple cancer types and nine drugs, and further reveals hierarchical structure across drugs and tissues in the visualization. These findings highlight the potential of biologically guided domain adaptation for improving translational pharmacogenomics.
EMOD: A Unified EEG Emotion Representation Framework Leveraging V-A Guided Contrastive Learning
PDF ↗Emotion recognition from EEG signals is essential for affective computing and has been widely explored using deep learning. While recent deep learning approaches have achieved strong performance on single EEG emotion datasets, their generalization across datasets remains limited due to the heterogeneity in annotation schemes and data formats. Existing models typically require dataset-specific architectures tailored to input structure and lack semantic alignment across diverse emotion labels. To address these challenges, we propose EMOD: A Unified EEG Emotion Representation Framework Leveraging Valence–Arousal (V–A) Guided Contrastive Learning. EMOD learns transferable and emotion-aware representations from heterogeneous datasets by bridging both semantic and structural gaps. Specifically, we project discrete and continuous emotion labels into a unified V–A space and formulate a soft-weighted supervised contrastive loss that encourages emotionally similar samples to cluster in the latent space. To accommodate variable EEG formats, EMOD employs a flexible backbone comprising a Triple-Domain Encoder followed by a Spatial-Temporal Transformer, enabling robust extraction and integration of temporal, spectral, and spatial features. We pretrain EMOD on 8 public EEG datasets and evaluate its performance on three benchmark datasets. Experimental results show that EMOD achieves the state-of-the-art performance, demonstrating strong adaptability and generalization across diverse EEG-based emotion recognition scenarios.
Dual-Perspective Disentanglement: Learning Symmetric Group-Aware Representations for Cross-Domain Recommendation
PDF ↗Cross-Domain Recommendation (CDR) transfers user preferences from a source domain to alleviate data sparsity in a target domain. While disentangling representations into domain-specific and shared components is a common method, existing methods overlook user preference heterogeneity and item appeal heterogeneity. To this end, we propose DPGCDR, a Dual-Perspective Group-aware CDR method that learns symmetric group-aware representations from both user and item. Conceptually, DPGCDR dynamically clusters users into groups and items into themes, then symmetrically disentangles user preferences into group-specific and cross-group shared components, and item attributes into theme-specific and cross-theme shared components. We propose a two-stage training scheme: 1) an initial warm-up stage learns preliminary representations to dynamically cluster users and items into group and theme structures which generalize cross-domain scenarios into multi-group disentanglement analogous to multi-domain settings; 2) a fusion-based aggregation stage integrates these group/theme-specific components into unified global representations. Additionally, an information-theoretic alignment regularizer further ensures consistency and discriminability between global shared and group/theme-specific representations, facilitating effective knowledge transfer by explicitly modeling and preserving the inherent multi-group structure within cross-domain interactions. Extensive experiments show DPGCDR achieves state-of-the-art performance, with significant gains of up to 25% in HR@10 over baselines on datasets with heterogeneous interaction structures. Further analyses confirm our dynamic clustering mechanism effectively adapts to underlying data patterns, enabling fine-grained cross-domain knowledge transfer.
Deep hashing offers efficient storage and fast retrieval capabilities. As a result, it has been extensively applied to large‑scale retrieval tasks. To alleviate the dependence on high-quality annotated data, recent research has focused on unsupervised domain adaptive hashing methods, which aim to transfer knowledge from a label-rich source domain to a label-scarce target domain. However, in open-world scenarios, source domain labels are often inevitably noisy, which tends to undermine the quality of learned hash codes and induce considerable performance deterioration. To this end, we introduce a novel Robust Domain Adaptive Hashing (RDAH) method to jointly mitigate the adverse effects of label noise and domain discrepancy. Specifically, we first model the loss distribution of training samples using a two-component Gaussian mixture model to estimate each sample’s confidence, based on which the data is partitioned. Subsequently, we introduce a neighbor consistency-guided correction strategy, which leverages the semantic structure of high-confidence neighbors to perform weighted correction on noisy samples. Moreover, we design a dual-level cross-domain alignment mechanism that jointly mitigates domain shift from two complementary perspectives. Extensive experimental results validate the effectiveness and robustness of RDAH across multiple benchmark datasets.
While Graph Foundation Models (GFMs) have achieved notable progress across diverse tasks recently, their robustness under domain noise, structural perturbations, and adversarial attacks remains largely underexplored. A core limitation lies in inadequate modeling of hierarchical structural semantics, which are intrinsic priors and critical for generalization. In this work, we propose SA^2GFM, a robust GFM framework that enhances domain adaptable representations through Structure Aware Semantic Augmentation. First, to embed hierarchical structural priors, we transform entropy based encoding trees into structure aware textual prompts for feature augmentation. The enriched inputs are processed by a novel self supervised Information Bottleneck mechanism that distills robust and transferable representations through structure guided compression. To mitigate negative transfer in cross domain adaptation, we develop an expert adaptive routing mechanism that integrates a mixture of experts architecture with a null expert design. To enable efficient downstream adaptation, we propose a fine tuning module that optimizes hierarchical structures through joint intra and inter community structure learning. Extensive experiments validate the superiority of SA^2GFM in effectiveness and robustness against random noise and adversarial perturbations on node and graph classification, compared with nine state of the art baselines.
Multi-Domain Multi-Task (MDMT) recommendation aims to provide personalized recommendations by leveraging information across multiple domains and tasks. However, existing methods often suffer from spurious correlations between irrelevant features and the target, leading to negative transfer. To address this, we propose a Stable and Adaptive Fusion (SAF) framework for MDMT recommendation. SAF introduces a weighted Hilbert-Schmidt Independence Criterion (HSIC) loss to decorrelate irrelevant features from the target, learning sample weights that promote stable (i.e., robust to spurious correlations) representations in both bottom and expert layers. We employ Random Fourier Features (RFF) to enable scalable computation of the HSIC loss. We further employ adaptive feature and expert gating to select these stable features, enabling the model to capture intricate cross-domain and cross-task dependencies. The learned sample weights are also used to reweight the MDMT loss during training. Experiments on large-scale datasets show that SAF outperforms state-of-the-art baselines by up to 2% in AUC. To facilitate further research, we release a new industrial dataset with 30 million interactions across 3 domains and 2 tasks, with 300 features.
High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foreground objects. While interactive methods allow for target adjustment, their class-agnostic design restricts generalization across different categories. Furthermore, the scarcity of high-quality annotation has led to a reliance on inharmonious synthetic data, resulting in poor generalization to real-world scenarios. To this end, we propose a Foreground Consistent Learning model, dubbed as FCLM, to address the aforementioned issues. Specifically, we first introduce a Depth-Aware Distillation strategy where we transfer the depth-related knowledge for better foreground representation. Considering the data dilemma, we term the processing of synthetic data as domain adaptation problem where we propose a domain-invariant learning strategy to focus on foreground learning. To support interactive prediction, we contribute an Object-Oriented Decoder that can receive both visual and language prompts to predict the referring target. Experimental results show that our method quantitatively and qualitatively outperforms state-of-the-art methods.
Source-Free Object Detection (SFOD) aims to adapt a source-pretrained object detector to a target domain without access to source data. However, existing SFOD methods predominantly rely on internal knowledge from the source model, which limits their capacity to generalize across domains and often results in biased pseudo-labels, thereby hindering both transferability and discriminability. In contrast, Vision Foundation Models (VFMs), pretrained on massive and diverse data, exhibit strong perception capabilities and broad generalization, yet their potential remains largely untapped in the SFOD setting. In this paper, we propose a novel SFOD framework that leverages VFMs as external knowledge sources to jointly enhance feature alignment and label quality. Specifically, we design three VFM-based modules: (1) Patch-weighted Global Feature Alignment (PGFA) distills global features from VFMs using patch-similarity–based weighting to enhance global feature transferability; (2) Prototype-based Instance Feature Alignment (PIFA) performs instance-level contrastive learning guided by momentum-updated VFM prototypes; and (3) Dual-source Enhanced Pseudo-label Fusion (DEPF) fuses predictions from detection VFMs and teacher models via an entropy-aware strategy to yield more reliable supervision. Extensive experiments on six benchmarks demonstrate that our method achieves state-of-the-art SFOD performance, validating the effectiveness of integrating VFMs to simultaneously improve transferability and discriminability.
SWIFT：A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening
PDF ↗Although deep learning-based methods have achieved promising performance in Pansharpening, they generally suffer from severe performance degradation when applied to data from unseen sensors. Existing cross-domain strategies, including retraining, fine-tuning, and zero-shot methods, fail to simultaneously preserve model architecture and maintain low adaptation costs. Therefore, we are the first to define and address a novel task in the pansharpening field: enhancing a model's cross-sensor generalization at an extremely low cost while keeping the model architecture invariant. To tackle this task, we propose SWIFT (Sensitive Weight Identification for Fast Transfer), a plug-and-play framework. SWIFT first employs an unsupervised manifold-based sampling strategy to efficiently select a high-fidelity subset the most informative target-domain samples. It then leverages this subset to probe a source-domain pre-trained model, identifying and updating only the weight subset most sensitive to the domain shift by analyzing the gradient behavior of its parameters. Extensive experiments demonstrate that SWIFT can be applied to various deep learning models, boosting adaptation efficiency by up to 30-fold. On a single NVIDIA RTX 4090 GPU, this reduces adaptation time from hours to as little as one minute. The adapted models not only substantially outperform direct-transfer baselines but also achieve performance competitive with, or even superior to full retraining while using only 3% of the target domain dataset and adapting nearly 10% to 30% of the model’s parameters. This establishs a new state-of-the-art on the WorldView-2 and QuickBird datasets.
BeyondSparse: Facilitating Mamba to Enhance Cross-Domain 3D Semantic Segmentation in Adverse Weather
PDF ↗Domain generalization (DG) and domain adaptation (DA) for 3D semantic segmentation enable the model to maintain high performance while avoiding labor-intensive and time-consuming annotation of target-domain data. However, under adverse weather conditions, the injection of spatial noise will affect the reflectivity of LiDAR point clouds, exacerbate domain distribution discrepancies, and degrade the generalization ability of the model. Current methods mainly rely on sparse convolution-based architecture. Due to its limited receptive field, the model captures varying local geometric information when dealing with point clouds of different sparsities, thereby limiting its transferability. To this end, we propose BeyondSparse, a novel cross-domain 3D semantic segmentation method under adverse weather that incorporates a state-space model into a 3D sparse convolution-based architecture, sequentially modeling all features to learn domain-invariant representations. This method consists of two main components: domain feature decoupling and Mamba-based encoder. The former performs feature disentanglement before sequential modeling, while the latter performs global modeling on voxelized point cloud data. In addition, we introduce a token-style augmentation to capture the intrinsic properties of input data. Extensive experimental results demonstrate that our method outperforms SOTA competitors in both DG and DA tasks, for instance, achieving +4.6% and +0.8% mIoU on ``SynLiDAR to SemanticSTF''.
Domain-adaptive person search (DAPS) aims to transfer pedestrian detection and re-identification capabilities from a labeled source domain to an unlabeled target domain, yet faces critical challenges from domain shift: semantic confusion among overlapping instances, over-reliance on shallow features for look-alike targets, and poor discriminability of small-scale instances. To address these issues, we propose the Localization-Anchored Instance Discrimination (LAID) framework, which leverages spatial relationships between bounding boxes as auxiliary signals to enhance instance identity learning. LAID integrates three complementary strategies: 1) Cost-Aware Instance Matching (CAIM) uses IoU-based global optimal assignment to align current detections with historical identities, reducing overlap-induced misassociations; 2) Dual-Scope Contrastive Learning (DSCL) combines spatial separation constraints (for geometrically distant pairs) with global contrastive learning, prompting the model to learn deep discriminative features beyond superficial similarities; 3) Task-Sensitivity Alignment (TSA) aligns confidence distributions of detection and ReID heads via KL divergence, ensuring consistent pseudo-label generation. Extensive experiments on CUHK-SYSU and PRW datasets demonstrate that LAID outperforms state-of-the-art DAPS methods, validating its effectiveness in mitigating domain shift and narrowing the performance gap between supervised and domain-adaptive person search.
Accurate segmentation of neural structures in Electron Microscopy (EM) images is paramount for neuroscience. However, this task is challenged by intricate morphologies, low signal-to-noise ratios, and scarce annotations, limiting the accuracy and generalization of existing methods. To address these challenges, we seek to leverage the priors learned by visual foundation models on a vast amount of natural images to better tackle this task. Specifically, we propose a novel framework that can effectively transfer knowledge from Segment Anything 2 (SAM2), which is pre-trained on natural images, to the EM domain. We first use SAM2 to extract powerful, general-purpose features. To bridge the domain gap, we introduce a Feature-Guided Attention module that leverages semantic cues from SAM2 to guide a lightweight encoder, the Fine-Grained Encoder (FGE), in focusing on these challenging regions. Finally, a dual-affinity decoder generates both coarse and refined affinity maps. Experimental results demonstrate that our method achieves performance comparable to state-of-the-art (SOTA) approaches with the SAM2 weights frozen. Upon further fine-tuning on EM data, our method significantly outperforms existing SOTA methods. This study validates that transferring representations pre-trained on natural images, when combined with targeted domain-adaptive guidance, can effectively address the specific challenges in neuron segmentation.