Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of generalizability, and the necessity to incorporate multi-modal data effectively. A foundation model, which is a large-scale pre-trained AI model, offers a versatile base that can be adapted to a variety of specific tasks and contexts. Here, we present VIsualization and Segmentation Masked AutoEncoder (VIS-MAE), novel model weights specifically designed for medical imaging. Specifically, VIS-MAE is trained on a dataset of 2.5 million unlabeled images from various modalities (CT, MR, PET,X-rays, and ultrasound), using self-supervised learning techniques. It is then adapted to classification and segmentation tasks using explicit labels. VIS-MAE has high label efficiency, outperforming several benchmark models in both in-domain and out-of-domain applications. In addition, VIS-MAE has improved label efficiency as it can achieve similar performance to other models with a reduced amount of labeled training data (50% or 80%) compared to other pre-trained weights. VIS-MAE represents a significant advancement in medical imaging AI, offering a generalizable and robust solution for improving segmentation and classification tasks while reducing the data annotation workload. The source code of this work is available at https://github.com/lzl199704/VIS-MAE.
Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate event streams, to the best of our knowledge. We introduce a new paradigm for self-supervised learning for multivariate point processes using a transformer encoder. Specifically, we design a novel pre-training strategy for the encoder where we not only mask random event epochs but also insert randomly sampled "void" epochs where an event does not occur; this differs from the typical discrete-time pretext tasks such as word-masking in BERT but expands the effectiveness of masking to better capture continuous-time dynamics. To improve downstream tasks, we introduce a contrasting module that compares real events to simulated void instances. The pre-trained model can subsequently be fine-tuned on a potentially much smaller event dataset, similar conceptually to the typical transfer of popular pre-trained language models. We demonstrate the effectiveness of our proposed paradigm on the next-event prediction task using synthetic datasets and 3 real applications, observing a relative performance boost of as high as up to 20% compared to state-of-the-art models.
In this research, we present SLYKLatent, a novel approach for enhancing gaze estimation by addressing appearance instability challenges in datasets due to aleatoric uncertainties, covariant shifts, and test domain generalization. SLYKLatent utilizes Self-Supervised Learning for initial training with facial expression datasets, followed by refinement with a patch-based tri-branch network and an inverse explained variance-weighted training loss function. Our evaluation on benchmark datasets achieves a 10.9% improvement on Gaze360, supersedes top MPIIFaceGaze results with 3.8%, and leads on a subset of ETH-XGaze by 11.6%, surpassing existing methods by significant margins. Adaptability tests on RAF-DB and Affectnet show 86.4% and 60.9% accuracies, respectively. Ablation studies confirm the effectiveness of SLYKLatent's novel components.
Self-supervised learning (SSL) has been incorporated into many state-of-the-art models in various domains, where SSL defines pretext tasks based on unlabeled datasets to learn contextualized and robust representations. Recently, SSL has become a new trend in exploring the representation learning capability in the realm of tabular data, which is more challenging due to not having explicit relations for learning descriptive representations. This survey aims to systematically review and summarize the recent progress and challenges of SSL for non-sequential tabular data (SSL4NS-TD). We first present a formal definition of NS-TD and clarify its correlation to related studies. Then, these approaches are categorized into three groups - predictive learning, contrastive learning, and hybrid learning, with their motivations and strengths of representative methods in each direction. Moreover, application issues of SSL4NS-TD are presented, including automatic data engineering, cross-table transferability, and domain knowledge integration. In addition, we elaborate on existing benchmarks and datasets for NS-TD applications to analyze the performance of existing tabular models. Finally, we discuss the challenges of SSL4NS-TD and provide potential directions for future research. We expect our work to be useful in terms of encouraging more research on lowering the barrier to entry SSL for the tabular domain, and of improving the foundations for implicit tabular data.
Urban region profiling plays a crucial role in forecasting and decision-making in the context of dynamic and noisy urban environments. Existing methods often struggle with issues such as noise, data incompleteness, and security vulnerabilities. This paper proposes a novel framework, Enhanced Urban Region Profiling with Adversarial Self-Supervised Learning (EUPAS), to address these challenges. By combining adversarial contrastive learning with both supervised and self-supervised objectives, EUPAS ensures robust performance across various forecasting tasks such as crime prediction, check-in prediction, and land use classification. To enhance model resilience against adversarial attacks and noisy data, we incorporate several key components, including perturbation augmentation, trickster generator, and deviation copy generator. These innovations effectively improve the robustness of the embeddings, making EUPAS capable of handling the complexities and noise inherent in urban data. Experimental results show that EUPAS significantly outperforms state-of-the-art methods across multiple tasks, achieving improvements in prediction accuracy of up to 10.8%. Notably, our model excels in adversarial attack tests, demonstrating its resilience in real-world, security-sensitive applications. This work makes a substantial contribution to the field of urban analytics by offering a more robust and secure approach to forecasting and profiling urban regions. It addresses key challenges in secure, data-driven modeling, providing a stronger foundation for future urban analytics and decision-making applications.
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. A common task is to classify augmentations or different modalities of the data, which share semantic content (e.g. an object in an image) but differ in style (e.g. the object's location). Many approaches to self-supervised learning have been proposed, e.g. SimCLR, CLIP, and DINO, which have recently gained much attention for their representations achieving downstream performance comparable to supervised learning. However, a theoretical understanding of self-supervised methods eludes. Addressing this, we present a generative latent variable model for self-supervised learning and show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations, providing a unifying theoretical framework for these methods. The proposed model also justifies connections drawn to mutual information and the use of a ''projection head''. Learning representations by fitting the model generatively (termed SimVAE) improves performance over discriminative and other VAE-based methods on simple image benchmarks and significantly narrows the gap between generative and discriminative representation learning in more complex settings. Importantly, as our analysis predicts, SimVAE outperforms self-supervised learning where style information is required, taking an important step toward understanding self-supervised methods and achieving task-agnostic representations.
Graph property prediction tasks are important and numerous. While each task offers a small size of labeled examples, unlabeled graphs have been collected from various sources and at a large scale. A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks. However, the self-supervised task knowledge could not be aligned or sometimes conflicted with what the predictions needed. In this paper, we propose to extract the knowledge underlying the large set of unlabeled graphs as a specific set of useful data points to augment each property prediction model. We use a diffusion model to fully utilize the unlabeled graphs and design two new objectives to guide the model's denoising process with each task's labeled data to generate task-specific graph examples and their labels. Experiments demonstrate that our data-centric approach performs significantly better than fifteen existing various methods on fifteen tasks. The performance improvement brought by unlabeled data is visible as the generated labeled examples unlike the self-supervised learning.
In recent years, the foundation models have swept the computer vision field and facilitated the development of various tasks within different modalities. However, it remains an open question on how to design an infrared foundation model. In this paper, we propose InfMAE, a foundation model in infrared modality. We release an infrared dataset, called Inf30 to address the problem of lacking large-scale data for self-supervised learning in the infrared vision community. Besides, we design an information-aware masking strategy, which is suitable for infrared images. This masking strategy allows for a greater emphasis on the regions with richer information in infrared images during the self-supervised learning process, which is conducive to learning the generalized representation. In addition, we adopt a multi-scale encoder to enhance the performance of the pre-trained encoders in downstream tasks. Finally, based on the fact that infrared images do not have a lot of details and texture information, we design an infrared decoder module, which further improves the performance of downstream tasks. Extensive experiments show that our proposed method InfMAE outperforms other supervised methods and self-supervised learning methods in three downstream tasks.
Children learn powerful internal models of the world around them from a few years of egocentric visual experience. Can such internal models be learned from a child's visual experience with highly generic learning algorithms or do they require strong inductive biases? Recent advances in collecting large-scale, longitudinal, developmentally realistic video datasets and generic self-supervised learning (SSL) algorithms are allowing us to begin to tackle this nature vs. nurture question. However, existing work typically focuses on image-based SSL algorithms and visual capabilities that can be learned from static images (e.g. object recognition), thus ignoring temporal aspects of the world. To close this gap, here we train self-supervised video models on longitudinal, egocentric headcam recordings collected from a child over a two year period in their early development (6-31 months). The resulting models are highly effective at facilitating the learning of action concepts from a small number of labeled examples; they have favorable data size scaling properties; and they display emergent video interpolation capabilities. Video models also learn more accurate and more robust object representations than image-based models trained with the exact same data. These results suggest that important temporal aspects of a child's internal model of the world may be learnable from their visual experience using highly generic learning algorithms and without strong inductive biases.
Health modeling of lithium-ion batteries (LIBs) is crucial for safe and efficient energy management and carries significant socio-economic implications. Although Machine Learning (ML)-based State of Health (SOH) estimation methods have made significant progress in accuracy, the scarcity of high-quality LIB data remains a major obstacle. Existing transfer learning methods for cross-domain LIB SOH estimation have significantly alleviated the labeling burden of target LIB data, however, they still require sufficient unlabeled target data (UTD) for effective adaptation to the target domain. Collecting this UTD is challenging due to the time-consuming nature of degradation experiments. To address this issue, we introduce a practical Test-Time Training framework, BatteryTTT, which adapts the model continually using each UTD collected amidst degradation, thereby significantly reducing data collection time. To fully utilize each UTD, BatteryTTT integrates the inherent physical laws of modern LIBs into self-supervised learning, termed Physcics-Guided Test-Time Training. Additionally, we explore the potential of large language models (LLMs) in battery sequence modeling by evaluating their performance in SOH estimation through model reprogramming and prefix prompt adaptation. The combination of BatteryTTT and LLM modeling, termed GPT4Battery, achieves state-of-the-art generalization results across current LIB benchmarks. Furthermore, we demonstrate the practical value and scalability of our approach by deploying it in our real-world battery management system (BMS) for 300Ah large-scale energy storage LIBs.
Specific emitter identification (SEI) based on radio frequency fingerprinting (RFF) is a physical layer authentication method in the field of wireless network security. RFFs are unique features embedded in the electromagnetic waves, which come from the hard imperfections in the wireless devices. Deep learning has been applied to many SEI tasks due to its powerful feature extraction capabilities. However, the success of most methods hinges on massive and labeled samples, and few methods focus on a realistic scenario, where few samples are available and labeled. In this paper, to overcome data limitations, we propose a few-shot SEI (FS-SEI) method based on self-supervised learning and adversarial augmentation (SA2SEI). Specifically, to overcome the limitation of label dependence for auxiliary dataset, a novelty adversarial augmentation (Adv-Aug)-powered self-supervised learning is designed to pre-train a RFF extractor using unlabeled auxiliary dataset. Subsequently, to overcome the limitation of sample dependence, knowledge transfer is introduced to fine-tune the extractor and a classifier with target dataset including few samples (5-30 samples per emitter in this paper) and corresponding labels. In addition, auxiliary dataset and target dataset are come from different emitters. An open-source large-scale real-world automatic-dependent surveillance-broadcast (ADS-B) dataset and a Wi-Fi dataset are used to evaluate the proposed SA2SEI method. The simulation results show that the proposed method can extract more discriminative RFF features and obtain higher identification performance in the FS-SEI. Specifically, when there are only 5 samples per Wi-Fi device, it can achieve 83.40% identification accuracy, in which 38.63% identification accuracy improvement comes from the Adv-Aug of pre-training process. The codes are available at https://github.com/LIUC-000/SA2SEI .
Video self-supervised learning (VSSL) has made significant progress in recent years. However, the exact behavior and dynamics of these models under different forms of distribution shift are not yet known. In this paper, we comprehensively study the behavior of six popular self-supervised methods (v-SimCLR, v-MoCo, v-BYOL, v-SimSiam, v-DINO, v-MAE) in response to various forms of natural distribution shift, i.e., (i) context shift, (ii) viewpoint shift, (iii) actor shift, (iv) source shift, (v) generalizability to unknown classes (zero-shot), and (vi) open-set recognition. To perform this extensive study, we carefully craft a test bed consisting of 17 in-distribution and out-of-distribution benchmark pairs using available public datasets and a series of evaluation protocols to stress-test the different methods under the intended shifts. Our study uncovers a series of intriguing findings and interesting behaviors of VSSL methods. For instance, we observe that while video models generally struggle with context shifts, v-MAE and supervised learning exhibit more robustness. Moreover, our study shows that v-MAE is a strong temporal learner, whereas contrastive methods, v-SimCLR and v-MoCo, exhibit strong performances against viewpoint shifts. When studying the notion of open-set recognition, we notice a trade-off between closed-set and open-set recognition performance if the pretrained VSSL encoders are used without finetuning. We hope that our work will contribute to the development of robust video representation learning frameworks for various real-world scenarios. The project page and code are available at: https://pritamqu.github.io/OOD-VSSL.
Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speech SSL models, such as WavLM, employ masked prediction training to encode general-purpose representations. In contrast, speaker SSL models, exemplified by DINO-based models, adopt utterance-level training objectives primarily for speaker representation. Understanding how these models represent information is essential for refining model efficiency and effectiveness. Unlike the various analyses of speech SSL, there has been limited investigation into what information speaker SSL captures and how its representation differs from speech SSL or other fully-supervised speaker models. This paper addresses these fundamental questions. We explore the capacity to capture various speech properties by applying SUPERB evaluation probing tasks to speech and speaker SSL models. We also examine which layers are predominantly utilized for each task to identify differences in how speech is represented. Furthermore, we conduct direct comparisons to measure the similarities between layers within and across models. Our analysis unveils that 1) the capacity to represent content information is somewhat unrelated to enhanced speaker representation, 2) specific layers of speech SSL models would be partly specialized in capturing linguistic information, and 3) speaker SSL models tend to disregard linguistic information but exhibit more sophisticated speaker representation.
Recent breakthroughs in scale have enabled the emergence of powerful generative language models, and the ability to fine-tune these models on various tasks by casting them into prompts or instructions. In this landscape, the problem of Unsupervised Domain Adaptation (UDA), or the problem of leveraging knowledge from a labeled source domain to an unlabeled target domain, has been left behind, with recent UDA methods still addressing discriminative classification. In particular, two popular UDA approaches, involving Continued Pre-Training (CPT) and learning domain invariant representations, have been under-explored in the generative setting, signaling a gap. In this work, we evaluate the utility of CPT for generative UDA. We first perform an empirical evaluation to measure the trade-offs between CPT and strong methods promoting domain invariance. We further evaluate how well the benefits of CPT extend to different architectures, tuning methods and data regimes. We then motivate the use of CPT by studying to what degree it benefits classification performance on the target domain. Finally, we attempt to understand the mechanism behind which CPT improves classification performance on the unlabeled target domain. Our findings suggest that a implicitly learns the downstream task while predicting masked words informative to that task. Our work connects the body of UDA research with that of instruction tuning, enabling an initial step towards a wider applicability of modern language models.
Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking. This way, the videos for MvMHAT require more complex annotations while containing more information for self learning. In this work, we tackle this problem with a self-supervised learning aware end-to-end network. Specifically, we propose to take advantage of the spatial-temporal self-consistency rationale by considering three properties of reflexivity, symmetry and transitivity. Besides the reflexivity property that naturally holds, we design the self-supervised learning losses based on the properties of symmetry and transitivity, for both appearance feature learning and assignment matrix optimization, to associate the multiple humans over time and across views. Furthermore, to promote the research on MvMHAT, we build two new large-scale benchmarks for the network training and testing of different algorithms. Extensive experiments on the proposed benchmarks verify the effectiveness of our method. We have released the benchmark and code to the public.
Self-supervised learning is the backbone of state of the art language modeling. It has been argued that training with predictive loss on a self-supervised dataset causes simulators: entities that internally represent possible configurations of real-world systems. Under this assumption, a mathematical model for simulators is built based in the Cartesian frames model of embedded agents, which is extended to multi-agent worlds through scaling a two-dimensional frame to arbitrary dimensions, where literature prior chooses to instead use operations on frames. This variant leveraging scaling dimensionality is named the Cartesian object, and is used to represent simulations (where individual simulacra are the agents and devices in that object). Around the Cartesian object, functions like token selection and simulation complexity are accounted for in formalizing the behavior of a simulator, and used to show (through the L\"obian obstacle) that a proof of alignment between simulacra by inspection of design is impossible in the simulator context. Following this, a scheme is proposed and termed Partial Simulation Extrapolation aimed at circumventing the L\"obian obstacle through the evaluation of low-complexity simulations.
One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities. Having robust and accurate representations derived from these modalities is key to enhancing the robustness and sample efficiency of RL algorithms. However, learning representations in RL settings for visuotactile data poses significant challenges, particularly due to the high dimensionality of the data and the complexity involved in correlating visual and tactile inputs with the dynamic environment and task objectives. To address these challenges, we propose Multimodal Contrastive Unsupervised Reinforcement Learning (M2CURL). Our approach employs a novel multimodal self-supervised learning technique that learns efficient representations and contributes to faster convergence of RL algorithms. Our method is agnostic to the RL algorithm, thus enabling its integration with any available RL algorithm. We evaluate M2CURL on the Tactile Gym 2 simulator and we show that it significantly enhances the learning efficiency in different manipulation tasks. This is evidenced by faster convergence rates and higher cumulative rewards per episode, compared to standard RL algorithms without our representation learning approach.
Monocular depth estimation (MDE) is a critical component of many medical tracking and mapping algorithms, particularly from endoscopic or laparoscopic video. However, because ground truth depth maps cannot be acquired from real patient data, supervised learning is not a viable approach to predict depth maps for medical scenes. Although self-supervised learning for MDE has recently gained attention, the outputs are difficult to evaluate reliably and each MDE's generalizability to other patients and anatomies is limited. This work evaluates the zero-shot performance of the newly released Depth Anything Model on medical endoscopic and laparoscopic scenes. We compare the accuracy and inference speeds of Depth Anything with other MDE models trained on general scenes as well as in-domain models trained on endoscopic data. Our findings show that although the zero-shot capability of Depth Anything is quite impressive, it is not necessarily better than other models in both speed and performance. We hope that this study can spark further research in employing foundation models for MDE in medical scenes.
This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build models. We provide several models, ranging from x-vector to recent SKA-TDNN. Through the modularized architecture design, variants can be developed easily. We also aspire to bridge developed models with other domains, facilitating the broad research community to effortlessly incorporate state-of-the-art embedding extractors. Pre-trained embedding extractors can be accessed in an off-the-shelf manner and we demonstrate the toolkit's versatility by showcasing its integration with two tasks. Another goal is to integrate with diverse self-supervised learning features. We release a reproducible recipe that achieves an equal error rate of 0.39% on the Vox1-O evaluation protocol using WavLM-Large with ECAPA-TDNN.
Deep Neural Network (DNN) models when implemented on executing devices as the inference engines are susceptible to Fault Injection Attacks (FIAs) that manipulate model parameters to disrupt inference execution with disastrous performance. This work introduces Contrastive Learning (CL) of visual representations i.e., a self-supervised learning approach into the deep learning training and inference pipeline to implement DNN inference engines with self-resilience under FIAs. Our proposed CL based FIA Detection and Recovery (CFDR) framework features (i) real-time detection with only a single batch of testing data and (ii) fast recovery effective even with only a small amount of unlabeled testing data. Evaluated with the CIFAR-10 dataset on multiple types of FIAs, our CFDR shows promising detection and recovery effectiveness.