Wearable Internet of Things (IoT) devices are gaining ground for continuous physiological data acquisition and health monitoring. These physiological signals can be used for security applications to achieve continuous authentication and user convenience due to passive data acquisition. This paper investigates an electrocardiogram (ECG) based biometric user authentication system using features derived from the Convolutional Neural Network (CNN) and self-supervised contrastive learning. Contrastive learning enables us to use large unlabeled datasets to train the model and establish its generalizability. We propose approaches enabling the CNN encoder to extract appropriate features that distinguish the user from other subjects. When evaluated using the PTB ECG database with 290 subjects, the proposed technique achieved an authentication accuracy of 99.15%. To test its generalizability, we applied the model to two new datasets, the MIT-BIH Arrhythmia Database and the ECG-ID Database, achieving over 98.5% accuracy without any modifications. Furthermore, we show that repeating the authentication step three times can increase accuracy to nearly 100% for both PTBDB and ECGIDDB. This paper also presents model optimizations for embedded device deployment, which makes the system more relevant to real-world scenarios. To deploy our model in IoT edge sensors, we optimized the model complexity by applying quantization and pruning. The optimized model achieves 98.67% accuracy on PTBDB, with 0.48% accuracy loss and 62.6% CPU cycles compared to the unoptimized model. An accuracy-vs-time-complexity tradeoff analysis is performed, and results are presented for different optimization levels.
In recent years, dynamic parameterization of acoustic environments has garnered attention in audio processing. This focus includes room volume and reverberation time (RT60), which define local acoustics independent of sound source and receiver orientation. Previous studies show that purely attention-based models can achieve advanced results in room parameter estimation. However, their success relies on supervised pretrainings that require a large amount of labeled true values for room parameters and complex training pipelines. In light of this, we propose a novel Self-Supervised Blind Room Parameter Estimation (SS-BRPE) system. This system combines a purely attention-based model with self-supervised learning to estimate room acoustic parameters, from single-channel noisy speech signals. By utilizing unlabeled audio data for pretraining, the proposed system significantly reduces dependencies on costly labeled datasets. Our model also incorporates dynamic feature augmentation during fine-tuning to enhance adaptability and generalizability. Experimental results demonstrate that the SS-BRPE system not only achieves more superior performance in estimating room parameters than state-of-the-art (SOTA) methods but also effectively maintains high accuracy under conditions with limited labeled data. Code available at https://github.com/bjut-chunxiwang/SS-BRPE.
Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks, each requiring different speech information, poses significant challenges. To this purpose, we propose a progressive residual extraction based self-supervised learning method, named ProgRE. Specifically, we introduce two lightweight and specialized task modules into an encoder-style SSL backbone to enhance its ability to extract pitch variation and speaker information from speech. Furthermore, to prevent the interference of reinforced pitch variation and speaker information with irrelevant content information learning, we residually remove the information extracted by these two modules from the main branch. The main branch is then trained using HuBERT's speech masking prediction to ensure the performance of the Transformer's deep-layer features on content tasks. In this way, we can progressively extract pitch variation, speaker, and content representations from the input speech. Finally, we can combine multiple representations with diverse speech information using different layer weights to obtain task-specific representations for various downstream tasks. Experimental results indicate that our proposed method achieves joint performance improvements on various tasks, such as speaker identification, speech recognition, emotion recognition, speech enhancement, and voice conversion, compared to excellent SSL methods such as wav2vec2.0, HuBERT, and WavLM.
In the broader machine learning literature, data-generation methods demonstrate promising results by generating additional informative training examples via augmenting sparse labels. Such methods are less studied in graphs due to the intricate dependencies among nodes in complex topology structures. This paper presents a novel node generation method that infuses a small set of high-quality synthesized nodes into the graph as additional labeled nodes to optimally expand the propagation of labeled information. By simply infusing additional nodes, the framework is orthogonal to the graph learning and downstream classification techniques, and thus is compatible with most popular graph pre-training (self-supervised learning), semi-supervised learning, and meta-learning methods. The contribution lies in designing the generated node set by solving a novel optimization problem. The optimization places the generated nodes in a manner that: (1) minimizes the classification loss to guarantee training accuracy and (2) maximizes label propagation to low-confidence nodes in the downstream task to ensure high-quality propagation. Theoretically, we show that the above dual optimization maximizes the global confidence of node classification. Our Experiments demonstrate statistically significant performance improvements over 14 baselines on 10 publicly available datasets.
Obtaining the solution of constrained optimization problems as a function of parameters is very important in a multitude of applications, such as control and planning. Solving such parametric optimization problems in real time can present significant challenges, particularly when it is necessary to obtain highly accurate solutions or batches of solutions. To solve these challenges, we propose a learning-based iterative solver for constrained optimization which can obtain very fast and accurate solutions by customizing the solver to a specific parametric optimization problem. For a given set of parameters of the constrained optimization problem, we propose a first step with a neural network predictor that outputs primal-dual solutions of a reasonable degree of accuracy. This primal-dual solution is then improved to a very high degree of accuracy in a second step by a learned iterative solver in the form of a neural network. A novel loss function based on the Karush-Kuhn-Tucker conditions of optimality is introduced, enabling fully self-supervised training of both neural networks without the necessity of prior sampling of optimizer solutions. The evaluation of a variety of quadratic and nonlinear parametric test problems demonstrates that the predictor alone is already competitive with recent self-supervised schemes for approximating optimal solutions. The second step of our proposed learning-based iterative constrained optimizer achieves solutions with orders of magnitude better accuracy than other learning-based approaches, while being faster to evaluate than state-of-the-art solvers and natively allowing for GPU parallelization.
Learning meaningful and interpretable representations from high-dimensional volumetric magnetic resonance (MR) images is essential for advancing personalized medicine. While Vision Transformers (ViTs) have shown promise in handling image data, their application to 3D multi-contrast MR images faces challenges due to computational complexity and interpretability. To address this, we propose a novel state-space-model (SSM)-based masked autoencoder which scales ViT-like models to handle high-resolution data effectively while also enhancing the interpretability of learned representations. We propose a latent-to-spatial mapping technique that enables direct visualization of how latent features correspond to specific regions in the input volumes in the context of SSM. We validate our method on two key neuro-oncology tasks: identification of isocitrate dehydrogenase mutation status and 1p/19q co-deletion classification, achieving state-of-the-art accuracy. Our results highlight the potential of SSM-based self-supervised learning to transform radiomics analysis by combining efficiency and interpretability.
Recent progress of semantic point clouds analysis is largely driven by synthetic data (e.g., the ModelNet and the ShapeNet), which are typically complete, well-aligned and noisy free. Therefore, representations of those ideal synthetic point clouds have limited variations in the geometric perspective and can gain good performance on a number of 3D vision tasks such as point cloud classification. In the context of unsupervised domain adaptation (UDA), representation learning designed for synthetic point clouds can hardly capture domain invariant geometric patterns from incomplete and noisy point clouds. To address such a problem, we introduce a novel scheme for induced geometric invariance of point cloud representations across domains, via regularizing representation learning with two self-supervised geometric augmentation tasks. On one hand, a novel pretext task of predicting translation distances of augmented samples is proposed to alleviate centroid shift of point clouds due to occlusion and noises. On the other hand, we pioneer an integration of the relational self-supervised learning on geometrically-augmented point clouds in a cascade manner, utilizing the intrinsic relationship of augmented variants and other samples as extra constraints of cross-domain geometric features. Experiments on the PointDA-10 dataset demonstrate the effectiveness of the proposed method, achieving the state-of-the-art performance.
3D perception in LiDAR point clouds is crucial for a self-driving vehicle to properly act in 3D environment. However, manually labeling point clouds is hard and costly. There has been a growing interest in self-supervised pre-training of 3D perception models. Following the success of contrastive learning in images, current methods mostly conduct contrastive pre-training on point clouds only. Yet an autonomous driving vehicle is typically supplied with multiple sensors including cameras and LiDAR. In this context, we systematically study single modality, cross-modality, and multi-modality for contrastive learning of point clouds, and show that cross-modality wins over other alternatives. In addition, considering the huge difference between the training sources in 2D images and 3D point clouds, it remains unclear how to design more effective contrastive units for LiDAR. We therefore propose the instance-aware and similarity-balanced contrastive units that are tailored for self-driving point clouds. Extensive experiments reveal that our approach achieves remarkable performance gains over various point cloud models across the downstream perception tasks of LiDAR based 3D object detection and 3D semantic segmentation on the four popular benchmarks including Waymo Open Dataset, nuScenes, SemanticKITTI and ONCE.
Supervised machine learning for music information retrieval requires a large annotated training set, and is thus an expensive and time-consuming process. To circumvent this problem, we propose to train deep neural networks to perceive beats in musical recordings despite having little or no access to human annotations. The key idea is to train two fully convolutional networks in parallel, which we name “Zero-Note Samba” (ZeroNS): the first analyzes the percussive part of a musical piece whilst the second analyzes its non-percussive part. These networks learn a self-supervised pretext task of synchrony prediction (sync-pred), which simulates the ability of musicians to groove together when playing in the same band. Sync-pred encourages the two networks to return similar outputs if the underlying musical parts are synchronized, yet dissimilar outputs if the parts are out of sync. In practice, we obtain the instrumental parts from commercial recordings via an off-the-shelf source separation system: Spleeter. After self-supervised learning with sync-pred, ZeroNS produces a sparse output that resembles a beat detection function. When used in conjunction with a dynamic Bayesian network, ZeroNS surpasses the state of the art in unsupervised beat tracking. Furthermore, fine-tuning ZeroNS to a small set of labeled data (of the order of one to ten songs) matches the performance of a fully supervised network on 96 songs. Lastly, we show that pre-training a supervised model with sync-pred mitigates dataset bias and thus improves cross-dataset generalization, at no extra annotation cost.
Humans perceive the world through multisensory integration, blending the information of different modalities to adapt their behavior. Contrastive learning offers an appealing solution for multimodal self-supervised learning. Indeed, by considering each modality as a different view of the same entity, it learns to align features of different modalities in a shared representation space. However, this approach is intrinsically limited as it only learns shared or redundant information between modalities, while multimodal interactions can arise in other ways. In this work, we introduce CoMM, a Contrastive MultiModal learning strategy that enables the communication between modalities in a single multimodal space. Instead of imposing cross- or intra- modality constraints, we propose to align multimodal representations by maximizing the mutual information between augmented versions of these multimodal features. Our theoretical analysis shows that shared, synergistic and unique terms of information naturally emerge from this formulation, allowing us to estimate multimodal interactions beyond redundancy. We test CoMM both in a controlled and in a series of real-world settings: in the former, we demonstrate that CoMM effectively captures redundant, unique and synergistic information between modalities. In the latter, CoMM learns complex multimodal interactions and achieves state-of-the-art results on the six multimodal benchmarks.
In this paper, we introduce DetailCLIP: A Detail-Oriented CLIP to address the limitations of contrastive learning-based vision-language models, particularly CLIP, in handling detail-oriented and fine-grained tasks like segmentation. While CLIP and its variants excel in the global alignment of image and text representations, they often struggle to capture the fine-grained details necessary for precise segmentation. To overcome these challenges, we propose a novel framework that employs patch-level comparison of self-distillation and pixel-level reconstruction losses, enhanced with an attention-based token removal mechanism. This approach selectively retains semantically relevant tokens, enabling the model to focus on the image's critical regions aligned with the specific functions of our model, including textual information processing, patch comparison, and image reconstruction, ensuring that the model learns high-level semantics and detailed visual features. Our experiments demonstrate that DetailCLIP surpasses existing CLIP-based and traditional self-supervised learning (SSL) models in segmentation accuracy and exhibits superior generalization across diverse datasets. DetailCLIP represents a significant advancement in vision-language modeling, offering a robust solution for tasks that demand high-level semantic understanding and detailed feature extraction. https://github.com/KishoreP1/DetailCLIP.
Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, licensing, and inherent biases. Synthesizing data is one of the promising ways to solve these issues, yet pre-training solely on synthetic data has its own challenges. In this paper, we introduce an effective self-supervised learning framework for videos that leverages readily available and less costly static images. Specifically, we define the Pseudo Motion Generator (PMG) module that recursively applies image transformations to generate pseudo-motion videos from images. These pseudo-motion videos are then leveraged in masked video modeling. Our approach is applicable to synthetic images as well, thus entirely freeing video pre-training from data collection costs and other concerns in real data. Through experiments in action recognition tasks, we demonstrate that this framework allows effective learning of spatio-temporal features through pseudo-motion videos, significantly improving over existing methods which also use static images and partially outperforming those using both real and synthetic videos. These results uncover fragments of what video transformers learn through masked video modeling.
In this work, we apply state-of-the-art self-supervised learning techniques on a large dataset of seafloor imagery, \textit{BenthicNet}, and study their performance for a complex hierarchical multi-label (HML) classification downstream task. In particular, we demonstrate the capacity to conduct HML training in scenarios where there exist multiple levels of missing annotation information, an important scenario for handling heterogeneous real-world data collected by multiple research groups with differing data collection protocols. We find that, when using smaller one-hot image label datasets typical of local or regional scale benthic science projects, models pre-trained with self-supervision on a larger collection of in-domain benthic data outperform models pre-trained on ImageNet. In the HML setting, we find the model can attain a deeper and more precise classification if it is pre-trained with self-supervision on in-domain data. We hope this work can establish a benchmark for future models in the field of automated underwater image annotation tasks and can guide work in other domains with hierarchical annotations of mixed resolution.
Self-supervised learning (SSL) is an effective method for exploiting unlabelled data to learn a high-level embedding space that can be used for various downstream tasks. However, existing methods to monitor the quality of the encoder -- either during training for one model or to compare several trained models -- still rely on access to annotated data. When SSL methodologies are applied to new data domains, a sufficiently large labelled dataset may not always be available. In this study, we propose several evaluation metrics which can be applied on the embeddings of unlabelled data and investigate their viability by comparing them to linear probe accuracy (a common metric which utilizes an annotated dataset). In particular, we apply $k$-means clustering and measure the clustering quality with the silhouette score and clustering agreement. We also measure the entropy of the embedding distribution. We find that while the clusters did correspond better to the ground truth annotations as training of the network progressed, label-free clustering metrics correlated with the linear probe accuracy only when training with SSL methods SimCLR and MoCo-v2, but not with SimSiam. Additionally, although entropy did not always have strong correlations with LP accuracy, this appears to be due to instability arising from early training, with the metric stabilizing and becoming more reliable at later stages of learning. Furthermore, while entropy generally decreases as learning progresses, this trend reverses for SimSiam. More research is required to establish the cause for this unexpected behaviour. Lastly, we find that while clustering based approaches are likely only viable for same-architecture comparisons, entropy may be architecture-independent.
Current multimodal alignment strategies primarily use single or unified modality encoders, while optimizing the alignment on the original token space. Such a framework is easy to implement and incorporate with the pretrained knowledge, but might result in information bias. To deal with such issues, the joint encoding predictive architecture (JEPA) learns the alignment loss on the latent space, with a predictor to convert the input encoding to the output latent space. However, the application of JEPA in multimodal scenarios is limited so far. In this paper, we introduce M3-Jepa, a scalable multimodal alignment framework, with the predictor implemented by a multi-directional mixture of experts (MoE). We demonstrate the framework can maximize the mutual information with information theory derivations, by alternating the optimization between different uni-directional tasks. By thoroughly designed experiments, we show that M3-Jepa can obtain state-of-the-art performance on different modalities and tasks, generalize to unseen datasets and domains, and is computationally efficient in training and inference. Our study indicates that M3-Jepa might provide a new paradigm to self-supervised learning and open-world modeling.
Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate augmentation for effective feature learning. To address these challenges, we propose GS-PT, which integrates 3D Gaussian Splatting (3DGS) into point cloud self-supervised learning for the first time. Our pipeline utilizes transformers as the backbone for self-supervised pre-training and introduces novel contrastive learning tasks through 3DGS. Specifically, the transformers aim to reconstruct the masked point cloud. 3DGS utilizes multi-view rendered images as input to generate enhanced point cloud distributions and novel view images, facilitating data augmentation and cross-modal contrastive learning. Additionally, we incorporate features from depth maps. By optimizing these tasks collectively, our method enriches the tri-modal self-supervised learning process, enabling the model to leverage the correlation across 3D point clouds and 2D images from various modalities. We freeze the encoder after pre-training and test the model's performance on multiple downstream tasks. Experimental results indicate that GS-PT outperforms the off-the-shelf self-supervised learning methods on various downstream tasks including 3D object classification, real-world classifications, and few-shot learning and segmentation.
Recently, self-supervised learning (SSL) has been extensively studied. Theoretically, mutual information maximization (MIM) is an optimal criterion for SSL, with a strong theoretical foundation in information theory. However, it is difficult to directly apply MIM in SSL since the data distribution is not analytically available in applications. In practice, many existing methods can be viewed as approximate implementations of the MIM criterion. This work shows that, based on the invariance property of MI, explicit MI maximization can be applied to SSL under a generic distribution assumption, i.e., a relaxed condition of the data distribution. We further illustrate this by analyzing the generalized Gaussian distribution. Based on this result, we derive a loss function based on the MIM criterion using only second-order statistics. We implement the new loss for SSL and demonstrate its effectiveness via extensive experiments.
As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine selected samples and the corresponding labels are widely adopted because they yield high performances by generating data-dependent virtual data while easily migrating to various domains. This survey presents a comprehensive review of foundational mixup methods and their applications. We first elaborate on the training pipeline with mixup augmentations as a unified framework containing modules. A reformulated framework could contain various mixup methods and give intuitive operational procedures. Then, we systematically investigate the applications of mixup augmentations on vision downstream tasks, various data modalities, and some analysis \& theorems of mixup. Meanwhile, we conclude the current status and limitations of mixup research and point out further work for effective and efficient mixup augmentations. This survey can provide researchers with the current state of the art in mixup methods and provide some insights and guidance roles in the mixup arena. An online project with this survey is available at \url{https://github.com/Westlake-AI/Awesome-Mixup}.
In this paper, we propose a solution for the semi-supervised learning track (MER-SEMI) in MER2024. First, in order to enhance the performance of the feature extractor on sentiment classification tasks,we fine-tuned video and text feature extractors, specifically CLIP-vit-large and Baichuan-13B, using labeled data. This approach effectively preserves the original emotional information conveyed in the videos. Second, we propose an Audio-Guided Transformer (AGT) fusion mechanism, which leverages the robustness of Hubert-large, showing superior effectiveness in fusing both inter-channel and intra-channel information. Third, To enhance the accuracy of the model, we iteratively apply self-supervised learning by using high-confidence unlabeled data as pseudo-labels. Finally, through black-box probing, we discovered an imbalanced data distribution between the training and test sets. Therefore, We adopt a prior-knowledge-based voting mechanism. The results demonstrate the effectiveness of our strategy, ultimately earning us third place in the MER-SEMI track.
Generating user intent from a sequence of user interface (UI) actions is a core challenge in comprehensive UI understanding. Recent advancements in multimodal large language models (MLLMs) have led to substantial progress in this area, but their demands for extensive model parameters, computing power, and high latency makes them impractical for scenarios requiring lightweight, on-device solutions with low latency or heightened privacy. Additionally, the lack of high-quality datasets has hindered the development of such lightweight models. To address these challenges, we propose UI-JEPA, a novel framework that employs masking strategies to learn abstract UI embeddings from unlabeled data through self-supervised learning, combined with an LLM decoder fine-tuned for user intent prediction. We also introduce two new UI-grounded multimodal datasets, "Intent in the Wild" (IIW) and "Intent in the Tame" (IIT), designed for few-shot and zero-shot UI understanding tasks. IIW consists of 1.7K videos across 219 intent categories, while IIT contains 914 videos across 10 categories. We establish the first baselines for these datasets, showing that representations learned using a JEPA-style objective, combined with an LLM decoder, can achieve user intent predictions that match the performance of state-of-the-art large MLLMs, but with significantly reduced annotation and deployment resources. Measured by intent similarity scores, UI-JEPA outperforms GPT-4 Turbo and Claude 3.5 Sonnet by 10.0% and 7.2% respectively, averaged across two datasets. Notably, UI-JEPA accomplishes the performance with a 50.5x reduction in computational cost and a 6.6x improvement in latency in the IIW dataset. These results underscore the effectiveness of UI-JEPA, highlighting its potential for lightweight, high-performance UI understanding.