This paper introduces a cutting-edge method for enhancing recommender systems through the integration of generative self-supervised learning (SSL) with a Residual Graph Transformer. Our approach emphasizes the importance of superior data enhancement through the use of pertinent pretext tasks, automated through rationale-aware SSL to distill clear ways of how users and items interact. The Residual Graph Transformer incorporates a topology-aware transformer for global context and employs residual connections to improve graph representation learning. Additionally, an auto-distillation process refines self-supervised signals to uncover consistent collaborative rationales. Experimental evaluations on multiple datasets demonstrate that our approach consistently outperforms baseline methods.
Bleed Air System (BAS) is critical for maintaining flight safety and operational efficiency, supporting functions such as cabin pressurization, air conditioning, and engine anti-icing. However, BAS malfunctions, including overpressure, low pressure, and overheating, pose significant risks such as cabin depressurization, equipment failure, or engine damage. Current diagnostic approaches face notable limitations when applied across different aircraft types, particularly for newer models that lack sufficient operational data. To address these challenges, this paper presents a self-supervised learning-based foundation model that enables the transfer of diagnostic knowledge from mature aircraft (e.g., A320, A330) to newer ones (e.g., C919). Leveraging self-supervised pretraining, the model learns universal feature representations from flight signals without requiring labeled data, making it effective in data-scarce scenarios. This model enhances both anomaly detection and baseline signal prediction, thereby improving system reliability. The paper introduces a cross-model dataset, a self-supervised learning framework for BAS diagnostics, and a novel Joint Baseline and Anomaly Detection Loss Function tailored to real-world flight data. These innovations facilitate efficient transfer of diagnostic knowledge across aircraft types, ensuring robust support for early operational stages of new models. Additionally, the paper explores the relationship between model capacity and transferability, providing a foundation for future research on large-scale flight signal models.
Asthma is a chronic respiratory condition that affects millions of people worldwide. While this condition can be managed by administering controller medications through handheld inhalers, clinical studies have shown low adherence to the correct inhaler usage technique. Consequently, many patients may not receive the full benefit of their medication. Automated classification of inhaler sounds has recently been studied to assess medication adherence. However, the existing classification models were typically trained using data from specific inhaler types, and their ability to generalize to sounds from different inhalers remains unexplored. In this study, we adapted the wav2vec 2.0 self-supervised learning model for inhaler sound classification by pre-training and fine-tuning this model on inhaler sounds. The proposed model shows a balanced accuracy of 98% on a dataset collected using a dry powder inhaler and smartwatch device. The results also demonstrate that re-finetuning this model on minimal data from a target inhaler is a promising approach to adapting a generic inhaler sound classification model to a different inhaler device and audio capture hardware. This is the first study in the field to demonstrate the potential of smartwatches as assistive technologies for the personalized monitoring of inhaler adherence using machine learning models.
Standard multimodal self-supervised learning (SSL) algorithms regard cross-modal synchronization as implicit supervisory labels during pretraining, thus posing high requirements on the scale and quality of multimodal samples. These constraints significantly limit the performance of sensing intelligence in IoT applications, as the heterogeneity and the non-interpretability of time-series signals result in abundant unimodal data but scarce high-quality multimodal pairs. This paper proposes InfoMAE, a cross-modal alignment framework that tackles the challenge of multimodal pair efficiency under the SSL setting by facilitating efficient cross-modal alignment of pretrained unimodal representations. InfoMAE achieves \textit{efficient cross-modal alignment} with \textit{limited data pairs} through a novel information theory-inspired formulation that simultaneously addresses distribution-level and instance-level alignment. Extensive experiments on two real-world IoT applications are performed to evaluate InfoMAE's pairing efficiency to bridge pretrained unimodal models into a cohesive joint multimodal model. InfoMAE enhances downstream multimodal tasks by over 60% with significantly improved multimodal pairing efficiency. It also improves unimodal task accuracy by an average of 22%.
We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding a new branch to selected attention layers that computes an auxiliary loss which we call the object-focused attention (OFA) loss. We restrict the attention to image patches that belong to the same object class, which allows ViTs to gain a better understanding of configural (or holistic) object shapes by focusing on intra-object patches instead of other patches such as those in the background. Our proposed inductive bias fits easily into the attention framework of transformers since it only adds an auxiliary loss over selected attention layers. Furthermore, our approach has no additional overhead during inference. We also experiment with multiscale masking to further improve the performance of our OFA model and give a path forward for self-supervised learning with our method. Our experimental results demonstrate that ViTs with OFA achieve better classification results than their base models, exhibit a stronger generalization ability to out-of-distribution (OOD) and adversarially corrupted images, and learn representations based on object shapes rather than spurious correlations via general textures. For our OOD setting, we generate a novel dataset using the COCO dataset and Stable Diffusion inpainting which we plan to share with the community.
Modern deep-learning architectures need large amounts of data to produce state-of-the-art results. Annotating such huge datasets is time-consuming, expensive, and prone to human error. Recent advances in self-supervised learning allow us to train huge models without explicit annotation. Contrastive learning is a popular paradigm in self-supervised learning. Recent works like SimCLR and CLIP rely on image augmentations or directly minimizing cross-modal loss between image and text. Banani et al. (2023) propose to use language guidance to sample view pairs. They claim that language enables better conceptual similarity, eliminating the effects of visual variability. We reproduce their experiments to verify their claims and find that their dataset, RedCaps, contains low-quality captions. We use an off-the-shelf image captioning model, BLIP-2, to replace the captions and improve performance, and we also devise a new metric to evaluate the semantic capabilities of self-supervised models based on interpretability methods.
We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, as current models struggle to obtain coherent image captions due to different camera viewpoints and clutter. We propose a three-phase framework to fine-tune existing captioning models that enhances caption accuracy and consistency across views via a consensus mechanism. First, an agent explores the environment, collecting noisy image-caption pairs. Then, a consistent pseudo-caption for each object instance is distilled via consensus using a large language model. Finally, these pseudo-captions are used to fine-tune an off-the-shelf captioning model, with the addition of contrastive learning. We analyse the performance of the combination of captioning models, exploration policies, pseudo-labeling methods, and fine-tuning strategies, on our manually labeled test set. Results show that a policy can be trained to mine samples with higher disagreement compared to classical baselines. Our pseudo-captioning method, in combination with all policies, has a higher semantic similarity compared to other existing methods, and fine-tuning improves caption accuracy and consistency by a significant margin. Code and test set annotations available at https://hsp-iit.github.io/embodied-captioning/
The number of studies that combine Evolutionary Machine Learning and self-supervised learning has been growing steadily in recent years. Evolutionary Machine Learning has been shown to help automate the design of machine learning algorithms and to lead to more reliable solutions. Self-supervised learning, on the other hand, has produced good results in learning useful features when labelled data is limited. This suggests that the combination of these two areas can help both in shaping evolutionary processes and in automating the design of deep neural networks, while also reducing the need for labelled data. Still, there are no detailed reviews that explain how Evolutionary Machine Learning and self-supervised learning can be used together. To help with this, we provide an overview of studies that bring these areas together. Based on this growing interest and the range of existing works, we suggest a new sub-area of research, which we call Evolutionary Self-Supervised Learning and introduce a taxonomy for it. Finally, we point out some of the main challenges and suggest directions for future research to help Evolutionary Self-Supervised Learning grow and mature as a field.
This work aims to characterise renal tumour microstructure using diffusion MRI (dMRI); via the Vascular, Extracellular and Restricted Diffusion for Cytometry in Tumours (VERDICT)-MRI framework with self-supervised learning. Comprehensive datasets were acquired from 14 patients with 15 biopsy-confirmed renal tumours, with nine b-values in the range b=[0,2500]s/mm2. A three-compartment VERDICT model for renal tumours was fitted to the dMRI data using a self-supervised deep neural network, and ROIs were drawn by an experienced uroradiologist. An economical acquisition protocol for future studies with larger patient cohorts was optimised using a recursive feature selection approach. The VERDICT model described the diffusion data in renal tumours more accurately than IVIM or ADC. Combined with self-supervised deep learning, VERDICT identified significant differences in the intracellular volume fraction between cancerous and normal tissue, and in the vascular volume fraction between vascular and non-vascular. The feature selector yields a 4 b-value acquisition of b = [70,150,1000,2000], with a duration of 14 minutes.
Data augmentation is a central component of joint embedding self-supervised learning (SSL). Approaches that work for natural images may not always be effective in medical imaging tasks. This study systematically investigated the impact of data augmentation and preprocessing strategies in SSL for lung ultrasound. Three data augmentation pipelines were assessed: (1) a baseline pipeline commonly used across imaging domains, (2) a novel semantic-preserving pipeline designed for ultrasound, and (3) a distilled set of the most effective transformations from both pipelines. Pretrained models were evaluated on multiple classification tasks: B-line detection, pleural effusion detection, and COVID-19 classification. Experiments revealed that semantics-preserving data augmentation resulted in the greatest performance for COVID-19 classification - a diagnostic task requiring global image context. Cropping-based methods yielded the greatest performance on the B-line and pleural effusion object classification tasks, which require strong local pattern recognition. Lastly, semantics-preserving ultrasound image preprocessing resulted in increased downstream performance for multiple tasks. Guidance regarding data augmentation and preprocessing strategies was synthesized for practitioners working with SSL in ultrasound.
Heart diseases constitute the main cause of international human defunction. According to the World Health Organization (WHO), approximately 18 million deaths happen each year due to precisely heart diseases. In particular, heart failures (HF) press the healthcare industry to develop systems for their early, rapid, and effective prediction. This work presents an automatic system based on a novel deep learning framework which analyses in real-time echocardiography video sequences for the challenging and more specific task of heart failure time prediction. This system works in two stages. The first one transforms the data from a database of echocardiography video sequences into a machine learning-compatible collection of annotated images which can be used in the training phase of any machine learning-based framework, including a deep learning-based one. This stage includes the use of the Higher Order Dynamic Mode Decomposition (HODMD) algorithm for both data augmentation and feature extraction. The second stage builds and trains a Vision Transformer (ViT). Self-supervised learning (SSL) methods, so far barely explored in the literature about heart failure prediction, are adopted to effectively train the ViT from scratch, even with scarce databases. The designed neural network analyses images from echocardiography sequences to estimate the time in which a heart failure will happen. The results obtained show the efficacy of the HODMD algorithm and the superiority of the proposed system with respect to several established ViT and Convolutional Neural Network (CNN) architectures. The source code will be incorporated into the next version release of the ModelFLOWs-app software (https://github.com/modelflows/ModelFLOWs-app).
Foundation Models, pre-trained on large unlabelled datasets before task-specific fine-tuning, are increasingly being applied to specialised domains. Recent examples include ClimaX for climate and Clay for satellite Earth observation, but a Foundation Model for Space Object Behavioural Analysis has not yet been developed. As orbital populations grow, automated methods for characterising space object behaviour are crucial for space safety. We present a Space Safety and Sustainability Foundation Model focusing on space object behavioural analysis using light curves (LCs). We implemented a Perceiver-Variational Autoencoder (VAE) architecture, pre-trained with self-supervised reconstruction and masked reconstruction on 227,000 LCs from the MMT-9 observatory. The VAE enables anomaly detection, motion prediction, and LC generation. We fine-tuned the model for anomaly detection & motion prediction using two independent LC simulators (CASSANDRA and GRIAL respectively), using CAD models of boxwing, Sentinel-3, SMOS, and Starlink platforms. Our pre-trained model achieved a reconstruction error of 0.01%, identifying potentially anomalous light curves through reconstruction difficulty. After fine-tuning, the model scored 88% and 82% accuracy, with 0.90 and 0.95 ROC AUC scores respectively in both anomaly detection and motion mode prediction (sun-pointing, spin, etc.). Analysis of high-confidence anomaly predictions on real data revealed distinct patterns including characteristic object profiles and satellite glinting. Here, we demonstrate how self-supervised learning can simultaneously enable anomaly detection, motion prediction, and synthetic data generation from rich representations learned in pre-training. Our work therefore supports space safety and sustainability through automated monitoring and simulation capabilities.
Self-supervised learning has become a core technique in speech processing, but the high dimensionality of its representations makes discretization essential for improving efficiency. However, existing discretization methods still suffer from significant information loss, resulting in a notable performance gap compared to continuous representations. To overcome these limitations, we propose two quantization-based discretization methods: Product Quantization (PQ) and Random Product Quantization (RPQ). PQ partitions the original feature space into multiple subspaces and independently quantizes each sub-vector, producing a fused set of discrete units that retain diverse information from different subspaces, thus mitigating the loss associated with single-cluster quantization. RPQ further enhances representation diversity by randomly sampling a fixed proportion of feature dimensions multiple times to construct sub-vectors, thereby better capturing the variability in the data distribution. Theoretical analysis shows that RPQ reduces the correlation coefficient rho (where 0 <= rho <= 1) between sub-quantizers. Its quantization error is lower-bounded by the product of rho and epsilon-kms, where epsilon-kms denotes the quantization error of a single K-means quantizer. Experimental results on a combined dataset built from LibriSpeech and ML-SUPERB show that PQ and RPQ outperform standard K-means discretization, achieving relative improvements of 21.8 percent and 20.0 percent in WER on LibriSpeech, and 24.1 percent and 19.6 percent in CER on ML-SUPERB, respectively. Moreover, their performance is competitive with, and in some cases even surpasses, that of continuous SSL representations.
In this paper, we consider the distributed optimal control problem for linear networked systems. In particular, we are interested in learning distributed optimal controllers using graph recurrent neural networks (GRNNs). Most of the existing approaches result in centralized optimal controllers with offline training processes. However, as the increasing demand of network resilience, the optimal controllers are further expected to be distributed, and are desirable to be trained in an online distributed fashion, which are also the main contributions of our work. To solve this problem, we first propose a GRNN-based distributed optimal control method, and we cast the problem as a self-supervised learning problem. Then, the distributed online training is achieved via distributed gradient computation, and inspired by the (consensus-based) distributed optimization idea, a distributed online training optimizer is designed. Furthermore, the local closed-loop stability of the linear networked system under our proposed GRNN-based controller is provided by assuming that the nonlinear activation function of the GRNN-based controller is both local sector-bounded and slope-restricted. The effectiveness of our proposed method is illustrated by numerical simulations using a specifically developed simulator.
The rapid advancement of audio generation technologies has escalated the risks of malicious deepfake audio across speech, sound, singing voice, and music, threatening multimedia security and trust. While existing countermeasures (CMs) perform well in single-type audio deepfake detection (ADD), their performance declines in cross-type scenarios. This paper is dedicated to studying the alltype ADD task. We are the first to comprehensively establish an all-type ADD benchmark to evaluate current CMs, incorporating cross-type deepfake detection across speech, sound, singing voice, and music. Then, we introduce the prompt tuning self-supervised learning (PT-SSL) training paradigm, which optimizes SSL frontend by learning specialized prompt tokens for ADD, requiring 458x fewer trainable parameters than fine-tuning (FT). Considering the auditory perception of different audio types,we propose the wavelet prompt tuning (WPT)-SSL method to capture type-invariant auditory deepfake information from the frequency domain without requiring additional training parameters, thereby enhancing performance over FT in the all-type ADD task. To achieve an universally CM, we utilize all types of deepfake audio for co-training. Experimental results demonstrate that WPT-XLSR-AASIST achieved the best performance, with an average EER of 3.58% across all evaluation sets. The code is available online.
In this work, we introduce long-video masked-embedding autoencoders (LV-MAE), a self-supervised learning framework for long video representation. Our approach treats short- and long-span dependencies as two separate tasks. Such decoupling allows for a more intuitive video processing where short-span spatiotemporal primitives are first encoded and are then used to capture long-range dependencies across consecutive video segments. To achieve this, we leverage advanced off-the-shelf multimodal encoders to extract representations from short segments within the long video, followed by pre-training a masked-embedding autoencoder capturing high-level interactions across segments. LV-MAE is highly efficient to train and enables the processing of much longer videos by alleviating the constraint on the number of input frames. Furthermore, unlike existing methods that typically pre-train on short-video datasets, our approach offers self-supervised pre-training using long video samples (e.g., 20+ minutes video clips) at scale. Using LV-MAE representations, we achieve state-of-the-art results on three long-video benchmarks -- LVU, COIN, and Breakfast -- employing only a simple classification head for either attentive or linear probing. Finally, to assess LV-MAE pre-training and visualize its reconstruction quality, we leverage the video-language aligned space of short video representations to monitor LV-MAE through video-text retrieval.
This study addresses the essential task of medical image segmentation, which involves the automatic identification and delineation of anatomical structures and pathological regions in medical images. Accurate segmentation is crucial in radiology, as it aids in the precise localization of abnormalities such as tumors, thereby enabling effective diagnosis, treatment planning, and monitoring of disease progression. Specifically, the size, shape, and location of tumors can significantly influence clinical decision-making and therapeutic strategies, making accurate segmentation a key component of radiological workflows. However, challenges posed by variations in MRI modalities, image artifacts, and the scarcity of labeled data complicate the segmentation task and impact the performance of traditional models. To overcome these limitations, we propose a novel self-supervised learning Multi-encoder nnU-Net architecture designed to process multiple MRI modalities independently through separate encoders. This approach allows the model to capture modality-specific features before fusing them for the final segmentation, thus improving accuracy. Our Multi-encoder nnU-Net demonstrates exceptional performance, achieving a Dice Similarity Coefficient (DSC) of 93.72%, which surpasses that of other models such as vanilla nnU-Net, SegResNet, and Swin UNETR. By leveraging the unique information provided by each modality, the model enhances segmentation tasks, particularly in scenarios with limited annotated data. Evaluations highlight the effectiveness of this architecture in improving tumor segmentation outcomes.
Existing debiasing approaches in Visual Question Answering (VQA) primarily focus on enhancing visual learning, integrating auxiliary models, or employing data augmentation strategies. However, these methods exhibit two major drawbacks. First, current debiasing techniques fail to capture the superior relation between images and texts because prevalent learning frameworks do not enable models to extract deeper correlations from highly contrasting samples. Second, they do not assess the relevance between the input question and image during inference, as no prior work has examined the degree of input relevance in debiasing studies. Motivated by these limitations, we propose a novel framework, Optimized Question-Image Relation Learning (QIRL), which employs a generation-based self-supervised learning strategy. Specifically, two modules are introduced to address the aforementioned issues. The Negative Image Generation (NIG) module automatically produces highly irrelevant question-image pairs during training to enhance correlation learning, while the Irrelevant Sample Identification (ISI) module improves model robustness by detecting and filtering irrelevant inputs, thereby reducing prediction errors. Furthermore, to validate our concept of reducing output errors through filtering unrelated question-image inputs, we propose a specialized metric to evaluate the performance of the ISI module. Notably, our approach is model-agnostic and can be integrated with various VQA models. Extensive experiments on VQA-CPv2 and VQA-v2 demonstrate the effectiveness and generalization ability of our method. Among data augmentation strategies, our approach achieves state-of-the-art results.
Masked Image Modeling (MIM) is a self-supervised learning technique that involves masking portions of an image, such as pixels, patches, or latent representations, and training models to predict the missing information using the visible context. This approach has emerged as a cornerstone in self-supervised learning, unlocking new possibilities in visual understanding by leveraging unannotated data for pre-training. In remote sensing, MIM addresses challenges such as incomplete data caused by cloud cover, occlusions, and sensor limitations, enabling applications like cloud removal, multi-modal data fusion, and super-resolution. By synthesizing and critically analyzing recent advancements, this survey (MIMRS) is a pioneering effort to chart the landscape of mask image modeling in remote sensing. We highlight state-of-the-art methodologies, applications, and future research directions, providing a foundational review to guide innovation in this rapidly evolving field.
The rapid advancement of foundation models has revolutionized visual representation learning in a self-supervised manner. However, their application in remote sensing (RS) remains constrained by a fundamental gap: existing models predominantly handle single or limited modalities, overlooking the inherently multi-modal nature of RS observations. Optical, synthetic aperture radar (SAR), and multi-spectral data offer complementary insights that significantly reduce the inherent ambiguity and uncertainty in single-source analysis. To bridge this gap, we introduce RingMoE, a unified multi-modal RS foundation model with 14.7 billion parameters, pre-trained on 400 million multi-modal RS images from nine satellites. RingMoE incorporates three key innovations: (1) A hierarchical Mixture-of-Experts (MoE) architecture comprising modal-specialized, collaborative, and shared experts, effectively modeling intra-modal knowledge while capturing cross-modal dependencies to mitigate conflicts between modal representations; (2) Physics-informed self-supervised learning, explicitly embedding sensor-specific radiometric characteristics into the pre-training objectives; (3) Dynamic expert pruning, enabling adaptive model compression from 14.7B to 1B parameters while maintaining performance, facilitating efficient deployment in Earth observation applications. Evaluated across 23 benchmarks spanning six key RS tasks (i.e., classification, detection, segmentation, tracking, change detection, and depth estimation), RingMoE outperforms existing foundation models and sets new SOTAs, demonstrating remarkable adaptability from single-modal to multi-modal scenarios. Beyond theoretical progress, it has been deployed and trialed in multiple sectors, including emergency response, land management, marine sciences, and urban planning.