PyTorchKR Papers

최신 논문

총 9,607편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.08829

Seal Your Backdoor with Variational Defense

We propose VIBE, a model-agnostic framework that trains classifiers resilient to backdoor attacks. The key concept behind our approach is to treat malicious inputs and corrupted labels from the training dataset as observed random variables, while the actual clean labels are latent. VIBE then recovers the corresponding latent clean label posterior through variational inference. The resulting training procedure follows the expectation-maximization (EM) algorithm. The E-step infers the clean pseudolabels by solving an entropy-regularized optimal transport problem, while the M-step updates the classifier parameters via gradient descent. Being modular, VIBE can seamlessly integrate with recent advancements in self-supervised representation learning, which enhance its ability to resist backdoor attacks. We experimentally validate the method effectiveness against contemporary backdoor attacks on standard datasets, a large-scale setup with 1$k$ classes, and a dataset poisoned with multiple attacks. VIBE consistently outperforms previous defenses across all tested scenarios.

arXiv:2503.08497공식 코드 · Papers with Code

MMRL: Multi-Modal Representation Learning for Vision-Language Models

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on new tasks. To tackle this issue, we propose a novel Multi-Modal Representation Learning (MMRL) framework that introduces a shared, learnable, and modality-agnostic representation space. MMRL projects the space tokens to text and image representation tokens, facilitating more effective multi-modal interactions. Unlike previous approaches that solely optimize class token features, MMRL integrates representation tokens at higher layers of the encoders--where dataset-specific features are more prominent--while preserving generalized knowledge in the lower layers. During training, both representation and class features are optimized, with trainable projection layer applied to the representation tokens, whereas the class token projection layer remains frozen to retain pre-trained knowledge. Furthermore, a regularization term is introduced to align the class features and text features with the zero-shot features from the frozen VLM, thereby safeguarding the model's generalization capacity. For inference, a decoupling strategy is employed, wherein both representation and class features are utilized for base classes, while only the class features, which retain more generalized knowledge, are used for new tasks. Extensive experiments across 15 datasets demonstrate that MMRL outperforms state-of-the-art methods, achieving a balanced trade-off between task-specific adaptation and generalization. Code is available at https://github.com/yunncheng/MMRL.

arXiv:2503.05626

FMT:A Multimodal Pneumonia Detection Model Based on Stacking MOE Framework

Artificial intelligence has shown the potential to improve diagnostic accuracy through medical image analysis for pneumonia diagnosis. However, traditional multimodal approaches often fail to address real-world challenges such as incomplete data and modality loss. In this study, a Flexible Multimodal Transformer (FMT) was proposed, which uses ResNet-50 and BERT for joint representation learning, followed by a dynamic masked attention strategy that simulates clinical modality loss to improve robustness; finally, a sequential mixture of experts (MOE) architecture was used to achieve multi-level decision refinement. After evaluation on a small multimodal pneumonia dataset, FMT achieved state-of-the-art performance with 94% accuracy, 95% recall, and 93% F1 score, outperforming single-modal baselines (ResNet: 89%; BERT: 79%) and the medical benchmark CheXMed (90%), providing a scalable solution for multimodal diagnosis of pneumonia in resource-constrained medical settings.

arXiv:2503.05319공식 코드 · Papers with Code

Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation

This paper discusses how ophthalmologists often rely on multimodal data to improve diagnostic accuracy. However, complete multimodal data is rare in real-world applications due to a lack of medical equipment and concerns about data privacy. Traditional deep learning methods typically address these issues by learning representations in latent space. However, the paper highlights two key limitations of these approaches: (i) Task-irrelevant redundant information (e.g., numerous slices) in complex modalities leads to significant redundancy in latent space representations. (ii) Overlapping multimodal representations make it difficult to extract unique features for each modality. To overcome these challenges, the authors propose the Essence-Point and Disentangle Representation Learning (EDRL) strategy, which integrates a self-distillation mechanism into an end-to-end framework to enhance feature selection and disentanglement for more robust multimodal learning. Specifically, the Essence-Point Representation Learning module selects discriminative features that improve disease grading performance. The Disentangled Representation Learning module separates multimodal data into modality-common and modality-unique representations, reducing feature entanglement and enhancing both robustness and interpretability in ophthalmic disease diagnosis. Experiments on multimodal ophthalmology datasets show that the proposed EDRL strategy significantly outperforms current state-of-the-art methods.

arXiv:2503.04812

LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning

Universal multimodal embedding models play a critical role in tasks such as interleaved image-text retrieval, multimodal RAG, and multimodal clustering. However, our empirical results indicate that existing LMM-based embedding models trained with the standard InfoNCE loss exhibit a high degree of overlap in similarity distribution between positive and negative pairs, making it challenging to distinguish hard negative pairs effectively. To deal with this issue, we propose a simple yet effective framework that dynamically improves the embedding model's representation learning for negative pairs based on their discriminative difficulty. Within this framework, we train a series of models, named LLaVE, and evaluate them on the MMEB benchmark, which covers 4 meta-tasks and 36 datasets. Experimental results show that LLaVE establishes stronger baselines that achieve state-of-the-art (SOTA) performance while demonstrating strong scalability and efficiency. Specifically, LLaVE-2B surpasses the previous SOTA 7B models, while LLaVE-7B achieves a further performance improvement of 6.2 points. Although LLaVE is trained on image-text data, it can generalize to text-video retrieval tasks in a zero-shot manner and achieve strong performance, demonstrating its remarkable potential for transfer to other embedding tasks.

arXiv:2503.06683

Dynamic Dictionary Learning for Remote Sensing Image Segmentation

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they often fail to dynamically adjust semantic embeddings according to contextual cues, leading to suboptimal performance in fine-grained scenarios such as cloud thickness differentiation. This work introduces a dynamic dictionary learning framework that explicitly models class ID embeddings through iterative refinement. The core contribution lies in a novel dictionary construction mechanism, where class-aware semantic embeddings are progressively updated via multi-stage alternating cross-attention querying between image features and dictionary embeddings. This process enables adaptive representation learning tailored to input-specific characteristics, effectively resolving ambiguities in intra-class heterogeneity and inter-class homogeneity. To further enhance discriminability, a contrastive constraint is applied to the dictionary space, ensuring compact intra-class distributions while maximizing inter-class separability. Extensive experiments across both coarse- and fine-grained datasets demonstrate consistent improvements over state-of-the-art methods, particularly in two online test benchmarks (LoveDA and UAVid). Code is available at https://anonymous.4open.science/r/D2LS-8267/.

arXiv:2503.06569

Global-Aware Monocular Semantic Scene Completion with State Space Models

Monocular Semantic Scene Completion (MonoSSC) reconstructs and interprets 3D environments from a single image, enabling diverse real-world applications. However, existing methods are often constrained by the local receptive field of Convolutional Neural Networks (CNNs), making it challenging to handle the non-uniform distribution of projected points (Fig. \ref{fig:perspective}) and effectively reconstruct missing information caused by the 3D-to-2D projection. In this work, we introduce GA-MonoSSC, a hybrid architecture for MonoSSC that effectively captures global context in both the 2D image domain and 3D space. Specifically, we propose a Dual-Head Multi-Modality Encoder, which leverages a Transformer architecture to capture spatial relationships across all features in the 2D image domain, enabling more comprehensive 2D feature extraction. Additionally, we introduce the Frustum Mamba Decoder, built on the State Space Model (SSM), to efficiently capture long-range dependencies in 3D space. Furthermore, we propose a frustum reordering strategy within the Frustum Mamba Decoder to mitigate feature discontinuities in the reordered voxel sequence, ensuring better alignment with the scan mechanism of the State Space Model (SSM) for improved 3D representation learning. We conduct extensive experiments on the widely used Occ-ScanNet and NYUv2 datasets, demonstrating that our proposed method achieves state-of-the-art performance, validating its effectiveness. The code will be released upon acceptance.

arXiv:2503.06451

A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification

Person Re-identification (ReID) systems that match individuals across images or video frames are essential in many real-world applications. However, existing methods are often influenced by attributes such as gender, pose, and body mass index (BMI), which vary in unconstrained settings and raise concerns related to fairness and generalization. To address this, we extend the notion of expressivity, defined as the mutual information between learned features and specific attributes, using a secondary neural network to quantify how strongly attributes are encoded. Applying this framework to three ReID models, we find that BMI consistently shows the highest expressivity in the final layers, indicating its dominant role in recognition. In the last attention layer, attributes are ranked as BMI > Pitch > Gender > Yaw, revealing their relative influences in representation learning. Expressivity values also evolve across layers and training epochs, reflecting a dynamic encoding of attributes. These findings demonstrate the central role of body attributes in ReID and establish a principled approach for uncovering attribute driven correlations.

arXiv:2503.06369

Spectral State Space Model for Rotation-Invariant~Visual~Representation~Learning

State Space Models (SSMs) have recently emerged as an alternative to Vision Transformers (ViTs) due to their unique ability of modeling global relationships with linear complexity. SSMs are specifically designed to capture spatially proximate relationships of image patches. However, they fail to identify relationships between conceptually related yet not adjacent patches. This limitation arises from the non-causal nature of image data, which lacks inherent directional relationships. Additionally, current vision-based SSMs are highly sensitive to transformations such as rotation. Their predefined scanning directions depend on the original image orientation, which can cause the model to produce inconsistent patch-processing sequences after rotation. To address these limitations, we introduce Spectral VMamba, a novel approach that effectively captures the global structure within an image by leveraging spectral information derived from the graph Laplacian of image patches. Through spectral decomposition, our approach encodes patch relationships independently of image orientation, achieving rotation invariance with the aid of our Rotational Feature Normalizer (RFN) module. Our experiments on classification tasks show that Spectral VMamba outperforms the leading SSM models in vision, such as VMamba, while maintaining invariance to rotations and a providing a similar runtime efficiency.

arXiv:2503.06361

Adversarial Robustness of Discriminative Self-Supervised Learning in Vision

Self-supervised learning (SSL) has advanced significantly in visual representation learning, yet comprehensive evaluations of its adversarial robustness remain limited. In this study, we evaluate the adversarial robustness of seven discriminative self-supervised models and one supervised model across diverse tasks, including ImageNet classification, transfer learning, segmentation, and detection. Our findings suggest that discriminative SSL models generally exhibit better robustness to adversarial attacks compared to their supervised counterpart on ImageNet, with this advantage extending to transfer learning when using linear evaluation. However, when fine-tuning is applied, the robustness gap between SSL and supervised models narrows considerably. Similarly, this robustness advantage diminishes in segmentation and detection tasks. We also investigate how various factors might influence adversarial robustness, including architectural choices, training duration, data augmentations, and batch sizes. Our analysis contributes to the ongoing exploration of adversarial robustness in visual self-supervised representation systems.

arXiv:2503.07202

A Zero-shot Learning Method Based on Large Language Models for Multi-modal Knowledge Graph Embedding

Zero-shot learning (ZL) is crucial for tasks involving unseen categories, such as natural language processing, image classification, and cross-lingual transfer. Current applications often fail to accurately infer and handle new relations or entities involving unseen categories, severely limiting their scalability and practicality in open-domain scenarios. ZL learning faces the challenge of effectively transferring semantic information of unseen categories in multi-modal knowledge graph (MMKG) embedding representation learning. In this paper, we propose ZSLLM, a framework for zero-shot embedding learning of MMKGs using large language models (LLMs). We leverage textual modality information of unseen categories as prompts to fully utilize the reasoning capabilities of LLMs, enabling semantic information transfer across different modalities for unseen categories. Through model-based learning, the embedding representation of unseen categories in MMKG is enhanced. Extensive experiments conducted on multiple real-world datasets demonstrate the superiority of our approach compared to state-of-the-art methods.

arXiv:2503.06132공식 코드 · Papers with Code

USP: Unified Self-Supervised Pretraining for Image Generation and Understanding

Recent studies have highlighted the interplay between diffusion models and representation learning. Intermediate representations from diffusion models can be leveraged for downstream visual tasks, while self-supervised vision models can enhance the convergence and generation quality of diffusion models. However, transferring pretrained weights from vision models to diffusion models is challenging due to input mismatches and the use of latent spaces. To address these challenges, we propose Unified Self-supervised Pretraining (USP), a framework that initializes diffusion models via masked latent modeling in a Variational Autoencoder (VAE) latent space. USP achieves comparable performance in understanding tasks while significantly improving the convergence speed and generation quality of diffusion models. Our code will be publicly available at https://github.com/cxxgtxy/USP.

arXiv:2503.07506

ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning

Active learning aims to select optimal samples for labeling, minimizing annotation costs. This paper introduces a unified representation learning framework tailored for active learning with task awareness. It integrates diverse sources, comprising reconstruction, adversarial, self-supervised, knowledge-distillation, and classification losses into a unified VAE-based ADROIT approach. The proposed approach comprises three key components - a unified representation generator (VAE), a state discriminator, and a (proxy) task-learner or classifier. ADROIT learns a latent code using both labeled and unlabeled data, incorporating task-awareness by leveraging labeled data with the proxy classifier. Unlike previous approaches, the proxy classifier additionally employs a self-supervised loss on unlabeled data and utilizes knowledge distillation to align with the target task-learner. The state discriminator distinguishes between labeled and unlabeled data, facilitating the selection of informative unlabeled samples. The dynamic interaction between VAE and the state discriminator creates a competitive environment, with the VAE attempting to deceive the discriminator, while the state discriminator learns to differentiate between labeled and unlabeled inputs. Extensive evaluations on diverse datasets and ablation analysis affirm the effectiveness of the proposed model.

arXiv:2503.06916

You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data

Data heterogeneity, stemming from local non-IID data and global long-tailed distributions, is a major challenge in federated learning (FL), leading to significant performance gaps compared to centralized learning. Previous research found that poor representations and biased classifiers are the main problems and proposed neural-collapse-inspired synthetic simplex ETF to help representations be closer to neural collapse optima. However, we find that the neural-collapse-inspired methods are not strong enough to reach neural collapse and still have huge gaps to centralized training. In this paper, we rethink this issue from a self-bootstrap perspective and propose FedYoYo (You Are Your Own Best Teacher), introducing Augmented Self-bootstrap Distillation (ASD) to improve representation learning by distilling knowledge between weakly and strongly augmented local samples, without needing extra datasets or models. We further introduce Distribution-aware Logit Adjustment (DLA) to balance the self-bootstrap process and correct biased feature representations. FedYoYo nearly eliminates the performance gap, achieving centralized-level performance even under mixed heterogeneity. It enhances local representation learning, reducing model drift and improving convergence, with feature prototypes closer to neural collapse optimality. Extensive experiments show FedYoYo achieves state-of-the-art results, even surpassing centralized logit adjustment methods by 5.4\% under global long-tailed settings.

arXiv:2503.06343공식 코드 · Papers with Code

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether the same information will be relevant to both the actor and the critic. To this end, we here explore the principles that underlie effective representations for the actor and for the critic in on-policy algorithms. We focus our study on understanding whether the actor and critic will benefit from separate, rather than shared, representations. Our primary finding is that when separated, the representations for the actor and critic systematically specialise in extracting different types of information from the environment -- the actor's representation tends to focus on action-relevant information, while the critic's representation specialises in encoding value and dynamics information. We conduct a rigourous empirical study to understand how different representation learning approaches affect the actor and critic's specialisations and their downstream performance, in terms of sample efficiency and generation capabilities. Finally, we discover that a separated critic plays an important role in exploration and data collection during training. Our code, trained models and data are accessible at https://github.com/francelico/deac-rep.

arXiv:2503.06112공식 코드 · Papers with Code

AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning

Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems, with the potential to replace Multilayer Perceptrons (MLPs). While many KANs are designed using basis and polynomial functions, such as B-splines, ReLU-KAN utilizes a combination of ReLU functions to mimic the structure of B-splines and take advantage of ReLU's speed. However, ReLU-KAN is not built for multiple inputs, and its limitations stem from ReLU's handling of negative values, which can restrict feature extraction. To address these issues, we introduce Activation Function-Based Kolmogorov-Arnold Networks (AF-KAN), expanding ReLU-KAN with various activations and their function combinations. This novel KAN also incorporates parameter reduction methods, primarily attention mechanisms and data normalization, to enhance performance on image classification datasets. We explore different activation functions, function combinations, grid sizes, and spline orders to validate the effectiveness of AF-KAN and determine its optimal configuration. In the experiments, AF-KAN significantly outperforms MLP, ReLU-KAN, and other KANs with the same parameter count. It also remains competitive even when using fewer than 6 to 10 times the parameters while maintaining the same network structure. However, AF-KAN requires a longer training time and consumes more FLOPs. The repository for this work is available at https://github.com/hoangthangta/All-KAN.

arXiv:2503.07444

Divide and Conquer Self-Supervised Learning for High-Content Imaging

Self-supervised representation learning methods often fail to learn subtle or complex features, which can be dominated by simpler patterns which are much easier to learn. This limitation is particularly problematic in applications to science and engineering, as complex features can be critical for discovery and analysis. To address this, we introduce Split Component Embedding Registration (SpliCER), a novel architecture which splits the image into sections and distils information from each section to guide the model to learn more subtle and complex features without compromising on simpler features. SpliCER is compatible with any self-supervised loss function and can be integrated into existing methods without modification. The primary contributions of this work are as follows: i) we demonstrate that existing self-supervised methods can learn shortcut solutions when simple and complex features are both present; ii) we introduce a novel self-supervised training method, SpliCER, to overcome the limitations of existing methods, and achieve significant downstream performance improvements; iii) we demonstrate the effectiveness of SpliCER in cutting-edge medical and geospatial imaging settings. SpliCER offers a powerful new tool for representation learning, enabling models to uncover complex features which could be overlooked by other methods.

arXiv:2503.05321

Riemannian Metric Learning: Closer to You than You Imagine

Riemannian metric learning is an emerging field in machine learning, unlocking new ways to encode complex data structures beyond traditional distance metric learning. While classical approaches rely on global distances in Euclidean space, they often fall short in capturing intrinsic data geometry. Enter Riemannian metric learning: a powerful generalization that leverages differential geometry to model the data according to their underlying Riemannian manifold. This approach has demonstrated remarkable success across diverse domains, from causal inference and optimal transport to generative modeling and representation learning. In this review, we bridge the gap between classical metric learning and Riemannian geometry, providing a structured and accessible overview of key methods, applications, and recent advances. We argue that Riemannian metric learning is not merely a technical refinement but a fundamental shift in how we think about data representations. Thus, this review should serve as a valuable resource for researchers and practitioners interested in exploring Riemannian metric learning and convince them that it is closer to them than they might imagine-both in theory and in practice.

arXiv:2503.04358

Learning Causal Response Representations through Direct Effect Analysis

We propose a novel approach for learning causal response representations. Our method aims to extract directions in which a multidimensional outcome is most directly caused by a treatment variable. By bridging conditional independence testing with causal representation learning, we formulate an optimisation problem that maximises the evidence against conditional independence between the treatment and outcome, given a conditioning set. This formulation employs flexible regression models tailored to specific applications, creating a versatile framework. The problem is addressed through a generalised eigenvalue decomposition. We show that, under mild assumptions, the distribution of the largest eigenvalue can be bounded by a known $F$-distribution, enabling testable conditional independence. We also provide theoretical guarantees for the optimality of the learned representation in terms of signal-to-noise ratio and Fisher information maximisation. Finally, we demonstrate the empirical effectiveness of our approach in simulation and real-world experiments. Our results underscore the utility of this framework in uncovering direct causal effects within complex, multivariate settings.

arXiv:2503.05933

Beyond H&E: Unlocking Pathological Insights with Polarization via Self-supervised Learning

Histopathology image analysis is fundamental to digital pathology, with hematoxylin and eosin (H&E) staining as the gold standard for diagnostic and prognostic assessments. While H&E imaging effectively highlights cellular and tissue structures, it lacks sensitivity to birefringence and tissue anisotropy, which are crucial for assessing collagen organization, fiber alignment, and microstructural alterations--key indicators of tumor progression, fibrosis, and other pathological conditions. To bridge this gap, we propose PolarHE, a dual modality fusion framework that integrates H&E with polarization imaging, leveraging the polarization ability to enhance tissue characterization. Our approach employs a feature decomposition strategy to disentangle common and modality specific features, ensuring effective multimodal representation learning. Through comprehensive validation, our approach significantly outperforms previous methods, achieving an accuracy of 86.70% on the Chaoyang dataset and 89.06% on the MHIST dataset. Moreover, polarization property visualization reveals distinct optical signatures of pathological tissues, highlighting its diagnostic potential. t-SNE visualizations further confirm our model effectively captures both shared and unique modality features, reinforcing the complementary nature of polarization imaging. These results demonstrate that polarization imaging is a powerful and underutilized modality in computational pathology, enriching feature representation and improving diagnostic accuracy. PolarHE establishes a promising direction for multimodal learning, paving the way for more interpretable and generalizable pathology models. Our code will be released after paper acceptance.