Current applications of self-supervised learning to wireless channel representation often borrow paradigms developed for text and image processing, without fully addressing the unique characteristics and constraints of wireless communications. Aiming to fill this gap, we first propose WiMAE (Wireless Masked Autoencoder), a transformer-based encoder-decoder foundation model pretrained on a realistic open-source multi-antenna wireless channel dataset. Building upon this foundation, we develop ContraWiMAE, which enhances WiMAE by incorporating a contrastive learning objective alongside the reconstruction task in a unified multi-task framework. By warm-starting from pretrained WiMAE weights and generating positive pairs via noise injection, the contrastive component enables the model to capture both structural and discriminative features, enhancing representation quality beyond what reconstruction alone can achieve. Through extensive evaluation on unseen scenarios, we demonstrate the effectiveness of both approaches across multiple downstream tasks, with ContraWiMAE showing further improvements in linear separability and adaptability in diverse wireless environments. Comparative evaluations against a state-of-the-art wireless channel foundation model confirm the superior performance and data efficiency of our models, highlighting their potential as powerful baselines for future research in self-supervised wireless channel representation learning.
Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to produce. Unsupervised approaches are typically trained to reconstruct the input signal, which is composed of the content and the speaker information. Disentangling these components is a challenge and often leads to speaker leakage or prosodic information removal. In this paper, we explore voice conversion by leveraging the potential of self-supervised learning (SSL). A combination of the latent representations of SSL models, concatenated with speaker embeddings, is fed to a vocoder which is trained to reconstruct the input. Zero-shot voice conversion results show that this approach allows to keep the prosody and content of the source speaker while matching the speaker similarity of a VC system based on phonetic posteriorgrams (PPGs).
Combinatorial Optimization (CO) encompasses a wide range of problems that arise in many real-world scenarios. While significant progress has been made in developing learning-based methods for specialized CO problems, a unified model with a single architecture and parameter set for diverse CO problems remains elusive. Such a model would offer substantial advantages in terms of efficiency and convenience. In this paper, we introduce UniCO, a unified model for solving various CO problems. Inspired by the success of next-token prediction, we frame each problem-solving process as a Markov Decision Process (MDP), tokenize the corresponding sequential trajectory data, and train the model using a transformer backbone. To reduce token length in the trajectory data, we propose a CO-prefix design that aggregates static problem features. To address the heterogeneity of state and action tokens within the MDP, we employ a two-stage self-supervised learning approach. In this approach, a dynamic prediction model is first trained and then serves as a pre-trained model for subsequent policy generation. Experiments across 10 CO problems showcase the versatility of UniCO, emphasizing its ability to generalize to new, unseen problems with minimal fine-tuning, achieving even few-shot or zero-shot performance. Our framework offers a valuable complement to existing neural CO methods that focus on optimizing performance for individual problems.
Self-supervised learning (SSL) models have significantly advanced speech processing tasks, and several benchmarks have been proposed to validate their effectiveness. However, previous benchmarks have primarily focused on single-speaker scenarios, with less exploration of target-speaker tasks in noisy, multi-talker conditions -- a more challenging yet practical case. In this paper, we introduce the Target-Speaker Speech Processing Universal Performance Benchmark (TS-SUPERB), which includes four widely recognized target-speaker processing tasks that require identifying the target speaker and extracting information from the speech mixture. In our benchmark, the speaker embedding extracted from enrollment speech is used as a clue to condition downstream models. The benchmark result reveals the importance of evaluating SSL models in target speaker scenarios, demonstrating that performance cannot be easily inferred from related single-speaker tasks. Moreover, by using a unified SSL-based target speech encoder, consisting of a speaker encoder and an extractor module, we also investigate joint optimization across TS tasks to leverage mutual information and demonstrate its effectiveness.
Recently, numerous pancreas segmentation methods have achieved promising performance on local single-source datasets. However, these methods don't adequately account for generalizability issues, and hence typically show limited performance and low stability on test data from other sources. Considering the limited availability of distinct data sources, we seek to improve the generalization performance of a pancreas segmentation model trained with a single-source dataset, i.e., the single source generalization task. In particular, we propose a dual self-supervised learning model that incorporates both global and local anatomical contexts. Our model aims to fully exploit the anatomical features of the intra-pancreatic and extra-pancreatic regions, and hence enhance the characterization of the high-uncertainty regions for more robust generalization. Specifically, we first construct a global-feature contrastive self-supervised learning module that is guided by the pancreatic spatial structure. This module obtains complete and consistent pancreatic features through promoting intra-class cohesion, and also extracts more discriminative features for differentiating between pancreatic and non-pancreatic tissues through maximizing inter-class separation. It mitigates the influence of surrounding tissue on the segmentation outcomes in high-uncertainty regions. Subsequently, a local-image restoration self-supervised learning module is introduced to further enhance the characterization of the high uncertainty regions. In this module, informative anatomical contexts are actually learned to recover randomly corrupted appearance patterns in those regions.
In this paper, we propose a diffusion model that integrates a representation-conditioning mechanism, where the representations derived from a Vision Transformer (ViT) are used to condition the internal process of a Transformer-based diffusion model. This approach enables representation-conditioned data generation, addressing the challenge of requiring large-scale labeled datasets by leveraging self-supervised learning on unlabeled data. We evaluate our method through a zero-shot classification task for hematoma detection in brain imaging. Compared to the strong contrastive learning baseline, DINOv2, our method achieves a notable improvement of +6.15% in accuracy and +13.60% in F1-score, demonstrating its effectiveness in image classification.
Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven illumination, irregular layout, occlusion, and degradation, resulting in performance disparities when handling complex real-world images. Recent self-supervised learning techniques, notably contrastive learning and masked image modeling (MIM), narrow this domain gap by exploiting unlabeled real text images. This study first analyzes the original Masked AutoEncoder (MAE) and observes that random patch masking predominantly captures low-level textural features but misses high-level contextual representations. To fully exploit the high-level contextual representations, we introduce random blockwise and span masking in the text recognition task. These strategies can mask the continuous image patches and completely remove some characters, forcing the model to infer relationships among characters within a word. Our Multi-Masking Strategy (MMS) integrates random patch, blockwise, and span masking into the MIM frame, which jointly learns low and high-level textual representations. After fine-tuning with real data, MMS outperforms the state-of-the-art self-supervised methods in various text-related tasks, including text recognition, segmentation, and text-image super-resolution.
Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the instance-level representation learning. They assume that the availability of a pre-trained feature extractor can be directly utilized or fine-tuned, which is not always the case. This paper proposes to pre-train feature extractor for MIL via a weakly-supervised scheme, i.e., propagating the weak bag-level labels to the corresponding instances for supervised learning. To learn effective features for MIL, we further delve into several key components, including strong data augmentation, a non-linear prediction head and the robust loss function. We conduct experiments on common large-scale WSI datasets and find it achieves better performance than other pre-training schemes (e.g., ImageNet pre-training and self-supervised learning) in different downstream tasks. We further show the compatibility and scalability of the proposed scheme by deploying it in fine-tuning the pathological-specific models and pre-training on merged multiple datasets. To our knowledge, this is the first work focusing on the representation learning for MIL.
Traffic accident prediction and detection are critical for enhancing road safety,and vision-based traffic accident anticipation (Vision-TAA) has emerged as a promising approach in the era of deep learning.This paper reviews 147 recent studies,focusing on the application of supervised,unsupervised,and hybrid deep learning models for accident prediction,alongside the use of real-world and synthetic datasets.Current methodologies are categorized into four key approaches: image and video feature-based prediction, spatiotemporal feature-based prediction, scene understanding,and multimodal data fusion.While these methods demonstrate significant potential,challenges such as data scarcity,limited generalization to complex scenarios,and real-time performance constraints remain prevalent. This review highlights opportunities for future research,including the integration of multimodal data fusion, self-supervised learning,and Transformer-based architectures to enhance prediction accuracy and scalability.By synthesizing existing advancements and identifying critical gaps, this paper provides a foundational reference for developing robust and adaptive Vision-TAA systems,contributing to road safety and traffic management.
Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer from notable limitations in recognition accuracy, convergence speed, and generalization, particularly in the complex and dynamic spectrum environments. To address these challenges, this paper proposes a novel spectrum foundation model, termed SpectrumFM, establishing a new paradigm for spectrum management. SpectrumFM features an innovative encoder architecture that synergistically exploits the convolutional neural networks and the multi-head self-attention mechanisms to enhance feature extraction and enable robust representation learning. The model is pre-trained via two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, which leverage large-scale in-phase and quadrature (IQ) data to achieve comprehensive and transferable spectrum representations. Furthermore, a parameter-efficient fine-tuning strategy is proposed to enable SpectrumFM to adapt to various downstream spectrum management tasks, including automatic modulation classification (AMC), wireless technology classification (WTC), spectrum sensing (SS), and anomaly detection (AD). Extensive experiments demonstrate that SpectrumFM achieves superior performance in terms of accuracy, robustness, adaptability, few-shot learning efficiency, and convergence speed, consistently outperforming conventional methods across multiple benchmarks. Specifically, SpectrumFM improves AMC accuracy by up to 12.1% and WTC accuracy by 9.3%, achieves an area under the curve (AUC) of 0.97 in SS at -4 dB signal-to-noise ratio (SNR), and enhances AD performance by over 10%.
Downstream probing has been the dominant method for evaluating model representations, an important process given the increasing prominence of self-supervised learning and foundation models. However, downstream probing primarily assesses the availability of task-relevant information in the model's latent space, overlooking attributes such as equivariance, invariance, and disentanglement, which contribute to the interpretability, adaptability, and utility of representations in real-world applications. While some attempts have been made to measure these qualities in representations, no unified evaluation framework with modular, generalizable, and interpretable metrics exists. In this paper, we argue for the importance of representation evaluation beyond downstream probing. We introduce a standardized protocol to quantify informativeness, equivariance, invariance, and disentanglement of factors of variation in model representations. We use it to evaluate representations from a variety of models in the image and speech domains using different architectures and pretraining approaches on identified controllable factors of variation. We find that representations from models with similar downstream performance can behave substantially differently with regard to these attributes. This hints that the respective mechanisms underlying their downstream performance are functionally different, prompting new research directions to understand and improve representations.
Purpose: Deep learning has demonstrated strong potential for MRI reconstruction, but conventional supervised learning methods require high-quality reference images, which are often unavailable in practice. Self-supervised learning offers an alternative, yet its performance degrades at high acceleration rates. To overcome these limitations, we propose hybrid learning, a novel two-stage training framework that combines self-supervised and supervised learning for robust image reconstruction. Methods: Hybrid learning is implemented in two sequential stages. In the first stage, self-supervised learning is employed to generate improved images from noisy or undersampled reference data. These enhanced images then serve as pseudo-ground truths for the second stage, which uses supervised learning to refine reconstruction performance and support higher acceleration rates. We evaluated hybrid learning in two representative applications: (1) accelerated 0.55T spiral-UTE lung MRI using noisy reference data, and (2) 3D T1 mapping of the brain without access to fully sampled ground truth. Results: For spiral-UTE lung MRI, hybrid learning consistently improved image quality over both self-supervised and conventional supervised methods across different acceleration rates, as measured by SSIM and NMSE. For 3D T1 mapping, hybrid learning achieved superior T1 quantification accuracy across a wide dynamic range, outperforming self-supervised learning in all tested conditions. Conclusions: Hybrid learning provides a practical and effective solution for training deep MRI reconstruction networks when only low-quality or incomplete reference data are available. It enables improved image quality and accurate quantitative mapping across different applications and field strengths, representing a promising technique toward broader clinical deployment of deep learning-based MRI.
The motion planning problem involves finding a collision-free path from a robot's starting to its target configuration. Recently, self-supervised learning methods have emerged to tackle motion planning problems without requiring expensive expert demonstrations. They solve the Eikonal equation for training neural networks and lead to efficient solutions. However, these methods struggle in complex environments because they fail to maintain key properties of the Eikonal equation, such as optimal value functions and geodesic distances. To overcome these limitations, we propose a novel self-supervised temporal difference metric learning approach that solves the Eikonal equation more accurately and enhances performance in solving complex and unseen planning tasks. Our method enforces Bellman's principle of optimality over finite regions, using temporal difference learning to avoid spurious local minima while incorporating metric learning to preserve the Eikonal equation's essential geodesic properties. We demonstrate that our approach significantly outperforms existing self-supervised learning methods in handling complex environments and generalizing to unseen environments, with robot configurations ranging from 2 to 12 degrees of freedom (DOF).
Magnetic resonance imaging (MRI) is a powerful noninvasive diagnostic imaging tool that provides unparalleled soft tissue contrast and anatomical detail. Noise contamination, especially in accelerated and/or low-field acquisitions, can significantly degrade image quality and diagnostic accuracy. Supervised learning based denoising approaches have achieved impressive performance but require high signal-to-noise ratio (SNR) labels, which are often unavailable. Self-supervised learning holds promise to address the label scarcity issue, but existing self-supervised denoising methods tend to oversmooth fine spatial features and often yield inferior performance than supervised methods. We introduce Corruption2Self (C2S), a novel score-based self-supervised framework for MRI denoising. At the core of C2S is a generalized denoising score matching (GDSM) loss, which extends denoising score matching to work directly with noisy observations by modeling the conditional expectation of higher-SNR images given further corrupted observations. This allows the model to effectively learn denoising across multiple noise levels directly from noisy data. Additionally, we incorporate a reparameterization of noise levels to stabilize training and enhance convergence, and introduce a detail refinement extension to balance noise reduction with the preservation of fine spatial features. Moreover, C2S can be extended to multi-contrast denoising by leveraging complementary information across different MRI contrasts. We demonstrate that our method achieves state-of-the-art performance among self-supervised methods and competitive results compared to supervised counterparts across varying noise conditions and MRI contrasts on the M4Raw and fastMRI dataset.
Self-supervised learning (SSL) has enabled Vision Transformers (ViTs) to learn robust representations from large-scale natural image datasets, enhancing their generalization across domains. In retinal imaging, foundation models pretrained on either natural or ophthalmic data have shown promise, but the benefits of in-domain pretraining remain uncertain. To investigate this, we benchmark six SSL-pretrained ViTs on seven digital fundus image (DFI) datasets totaling 70,000 expert-annotated images for the task of moderate-to-late age-related macular degeneration (AMD) identification. Our results show that iBOT pretrained on natural images achieves the highest out-of-distribution generalization, with AUROCs of 0.80-0.97, outperforming domain-specific models, which achieved AUROCs of 0.78-0.96 and a baseline ViT-L with no pretraining, which achieved AUROCs of 0.68-0.91. These findings highlight the value of foundation models in improving AMD identification and challenge the assumption that in-domain pretraining is necessary. Furthermore, we release BRAMD, an open-access dataset (n=587) of DFIs with AMD labels from Brazil.
We propose an input convex neural network (ICNN)-based self-supervised learning framework to solve continuous constrained optimization problems. By integrating the augmented Lagrangian method (ALM) with the constraint correction mechanism, our framework ensures \emph{non-strict constraint feasibility}, \emph{better optimality gap}, and \emph{best convergence rate} with respect to the state-of-the-art learning-based methods. We provide a rigorous convergence analysis, showing that the algorithm converges to a Karush-Kuhn-Tucker (KKT) point of the original problem even when the internal solver is a neural network, and the approximation error is bounded. We test our approach on a range of benchmark tasks including quadratic programming (QP), nonconvex programming, and large-scale AC optimal power flow problems. The results demonstrate that compared to existing solvers (e.g., \texttt{OSQP}, \texttt{IPOPT}) and the latest learning-based methods (e.g., DC3, PDL), our approach achieves a superior balance among accuracy, feasibility, and computational efficiency.
Video event detection has become an essential component of sports analytics, enabling automated identification of key moments and enhancing performance analysis, viewer engagement, and broadcast efficiency. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNNs) and Transformers, have significantly improved accuracy and efficiency in Temporal Action Localization (TAL), Action Spotting (AS), and Precise Event Spotting (PES). This survey provides a comprehensive overview of these three key tasks, emphasizing their differences, applications, and the evolution of methodological approaches. We thoroughly review and categorize existing datasets and evaluation metrics specifically tailored for sports contexts, highlighting the strengths and limitations of each. Furthermore, we analyze state-of-the-art techniques, including multi-modal approaches that integrate audio and visual information, methods utilizing self-supervised learning and knowledge distillation, and approaches aimed at generalizing across multiple sports. Finally, we discuss critical open challenges and outline promising research directions toward developing more generalized, efficient, and robust event detection frameworks applicable to diverse sports. This survey serves as a foundation for future research on efficient, generalizable, and multi-modal sports event detection.
Semiconductor manufacturing generates vast amounts of image data, crucial for defect identification and yield optimization, yet often exceeds manual inspection capabilities. Traditional clustering techniques struggle with high-dimensional, unlabeled data, limiting their effectiveness in capturing nuanced patterns. This paper introduces an advanced clustering framework that integrates deep Topological Data Analysis (TDA) with self-supervised and transfer learning techniques, offering a novel approach to unsupervised image clustering. TDA captures intrinsic topological features, while self-supervised learning extracts meaningful representations from unlabeled data, reducing reliance on labeled datasets. Transfer learning enhances the framework's adaptability and scalability, allowing fine-tuning to new datasets without retraining from scratch. Validated on synthetic and open-source semiconductor image datasets, the framework successfully identifies clusters aligned with defect patterns and process variations. This study highlights the transformative potential of combining TDA, self-supervised learning, and transfer learning, providing a scalable solution for proactive process monitoring and quality control in semiconductor manufacturing and other domains with large-scale image datasets.
Self-supervised learning has transformed 2D computer vision by enabling models trained on large, unannotated datasets to provide versatile off-the-shelf features that perform similarly to models trained with labels. However, in 3D scene understanding, self-supervised methods are typically only used as a weight initialization step for task-specific fine-tuning, limiting their utility for general-purpose feature extraction. This paper addresses this shortcoming by proposing a robust evaluation protocol specifically designed to assess the quality of self-supervised features for 3D scene understanding. Our protocol uses multi-resolution feature sampling of hierarchical models to create rich point-level representations that capture the semantic capabilities of the model and, hence, are suitable for evaluation with linear probing and nearest-neighbor methods. Furthermore, we introduce the first self-supervised model that performs similarly to supervised models when only off-the-shelf features are used in a linear probing setup. In particular, our model is trained natively in 3D with a novel self-supervised approach based on a Masked Scene Modeling objective, which reconstructs deep features of masked patches in a bottom-up manner and is specifically tailored to hierarchical 3D models. Our experiments not only demonstrate that our method achieves competitive performance to supervised models, but also surpasses existing self-supervised approaches by a large margin. The model and training code can be found at our Github repository (https://github.com/phermosilla/msm).
Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal redundancy, limiting their capability for semantic representation and sufficient encoding of motion dynamics. To address these issues, this paper introduces a novel SSL approach for video representation learning, dubbed as SMILE, by infusing both spatial and motion semantics. In SMILE, we leverage image-language pretrained models, such as CLIP, to guide the learning process with their high-level spatial semantics. We enhance the representation of motion by introducing synthetic motion patterns in the training data, allowing the model to capture more complex and dynamic content. Furthermore, using SMILE, we establish a new self-supervised video learning paradigm capable of learning strong video representations without requiring any natural video data. We have carried out extensive experiments on 7 datasets with various downstream scenarios. SMILE surpasses current state-of-the-art SSL methods, showcasing its effectiveness in learning more discriminative and generalizable video representations. Code is available: https://github.com/fmthoker/SMILE