Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily. However, most of the state-of-the-art event-stream representations are manually designed and the quality of these representations cannot be guaranteed due to the noisy nature of event-streams. In this paper, we introduce a data-driven approach aiming at enhancing the quality of event-stream representations. Our approach commences with the introduction of a new event-stream representation based on spatial-temporal statistics, denoted as EvRep. Subsequently, we theoretically derive the intrinsic relationship between asynchronous event-streams and synchronous video frames. Building upon this theoretical relationship, we train a representation generator, RepGen, in a self-supervised learning manner accepting EvRep as input. Finally, the event-streams are converted to high-quality representations, termed as EvRepSL, by going through the learned RepGen (without the need of fine-tuning or retraining). Our methodology is rigorously validated through extensive evaluations on a variety of mainstream event-based classification and optical flow datasets (captured with various types of event cameras). The experimental results highlight not only our approach's superior performance over existing event-stream representations but also its versatility, being agnostic to different event cameras and tasks.
Numerical weather prediction (NWP) models are fundamental in meteorology for simulating and forecasting the behavior of various atmospheric variables. The accuracy of precipitation forecasts and the acquisition of sufficient lead time are crucial for preventing hazardous weather events. However, the performance of NWP models is limited by the nonlinear and unpredictable patterns of extreme weather phenomena driven by temporal dynamics. In this regard, we propose a \textbf{S}elf-\textbf{S}upervised \textbf{L}earning with \textbf{P}robabilistic \textbf{D}ensity \textbf{L}abeling (SSLPDL) for estimating rainfall probability by post-processing NWP forecasts. Our post-processing method uses self-supervised learning (SSL) with masked modeling for reconstructing atmospheric physics variables, enabling the model to learn the dependency between variables. The pre-trained encoder is then utilized in transfer learning to a precipitation segmentation task. Furthermore, we introduce a straightforward labeling approach based on probability density to address the class imbalance in extreme weather phenomena like heavy rain events. Experimental results show that SSLPDL surpasses other precipitation forecasting models in regional precipitation post-processing and demonstrates competitive performance in extending forecast lead times. Our code is available at https://github.com/joonha425/SSLPDL
Osteoporosis is a widespread and chronic metabolic bone disease that often remains undiagnosed and untreated due to limited access to bone mineral density (BMD) tests like Dual-energy X-ray absorptiometry (DXA). In response to this challenge, current advancements are pivoting towards detecting osteoporosis by examining alternative indicators from peripheral bone areas, with the goal of increasing screening rates without added expenses or time. In this paper, we present a method to predict osteoporosis using hand and wrist X-ray images, which are both widely accessible and affordable, though their link to DXA-based data is not thoroughly explored. We employ a sophisticated image segmentation model that utilizes a mixture of probabilistic U-Net decoders, specifically designed to capture predictive uncertainty in the segmentation of the ulna, radius, and metacarpal bones. This model is formulated as an optimal transport (OT) problem, enabling it to handle the inherent uncertainties in image segmentation more effectively. Further, we adopt a self-supervised learning (SSL) approach to extract meaningful representations without the need for explicit labels, and move on to classify osteoporosis in a supervised manner. Our method is evaluated on a dataset with 192 individuals, cross-referencing their verified osteoporosis conditions against the standard DXA test. With a notable classification score, this integration of uncertainty-aware segmentation and self-supervised learning represents a pioneering effort in leveraging vision-based techniques for the early detection of osteoporosis from peripheral skeletal sites.
Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational cost poses a significant barrier to wider application. To enhance inference efficiency, most existing approaches depend on parameter-dependent or token-dependent strategies to reduce computational demands. However, these methods typically require complex training processes and struggle to consistently select the most relevant tokens. In this paper, we systematically analyze the above challenges and provide a series of valuable insights for inference acceleration. Based on these findings, we propose a novel framework, the Pruning All-Rounder (PAR). Different from previous works, PAR develops a meta-router to adaptively organize pruning flows across both tokens and layers. With a self-supervised learning manner, our method achieves a superior balance between performance and efficiency. Notably, PAR is highly flexible, offering multiple pruning versions to address a range of pruning scenarios. The code for this work will be made publicly available.
Event cameras provide low-latency perception for only milliwatts of power. This makes them highly suitable for resource-restricted, agile robots such as small flying drones. Self-supervised learning based on contrast maximization holds great potential for event-based robot vision, as it foregoes the need for high-frequency ground truth and allows for online learning in the robot's operational environment. However, online, on-board learning raises the major challenge of achieving sufficient computational efficiency for real-time learning, while maintaining competitive visual perception performance. In this work, we improve the time and memory efficiency of the contrast maximization pipeline, making on-device learning of low-latency monocular depth possible. We demonstrate that online learning on board a small drone yields more accurate depth estimates and more successful obstacle avoidance behavior compared to only pre-training. Benchmarking experiments show that the proposed pipeline is not only efficient, but also achieves state-of-the-art depth estimation performance among self-supervised approaches. Our work taps into the unused potential of online, on-device robot learning, promising smaller reality gaps and better performance.
Autonomous robots operating in real environments are often faced with decisions on how best to navigate their surroundings. In this work, we address a particular instance of this problem: how can a robot autonomously decide on the energetically optimal path to follow given a high-level objective and information about the surroundings? To tackle this problem we developed a self-supervised learning method that allows the robot to estimate the cost of transport of its surroundings using only vision inputs. We apply our method to the multi-modal mobility morphobot (M4), a robot that can drive, fly, segway, and crawl through its environment. By deploying our system in the real world, we show that our method accurately assigns different cost of transports to various types of environments e.g. grass vs smooth road. We also highlight the low computational cost of our method, which is deployed on an Nvidia Jetson Orin Nano robotic compute unit. We believe that this work will allow multi-modal robotic platforms to unlock their full potential for navigation and exploration tasks.
Query-driven learned estimators are accurate, flexible, and lightweight alternatives to traditional estimators in query optimization. However, existing query-driven approaches struggle with the Out-of-distribution (OOD) problem, where the test workload distribution differs from the training workload, leading to performancedegradation. In this paper, we present CardOOD, a general learning framework designed to construct robust query-driven cardinality estimators that are resilient against the OOD problem. Our framework focuses on offline training algorithms that develop one-off models from a static workload, suitable for model initialization and periodic retraining. In CardOOD, we extend classical transfer/robust learning techniques to train query-driven cardinalityestimators, and the algorithms fall into three categories: representation learning, data manipulation, and new learning strategies. As these learning techniques are originally evaluated in computervision tasks, we also propose a new learning algorithm that exploits the property of cardinality estimation. This algorithm, lying in the category of new learning strategy, models the partial order constraint of cardinalities by a self-supervised learning task. Comprehensive experimental studies demonstrate the efficacy of the algorithms of CardOOD in mitigating the OOD problem to varying extents. We further integrate CardOOD into PostgreSQL, showcasing its practical utility in query optimization.
We present Visual Lexicon, a novel visual language that encodes rich image information into the text space of vocabulary tokens while retaining intricate visual details that are often challenging to convey in natural language. Unlike traditional methods that prioritize either high-level semantics (e.g., CLIP) or pixel-level reconstruction (e.g., VAE), ViLex simultaneously captures rich semantic content and fine visual details, enabling high-quality image generation and comprehensive visual scene understanding. Through a self-supervised learning pipeline, ViLex generates tokens optimized for reconstructing input images using a frozen text-to-image (T2I) diffusion model, preserving the detailed information necessary for high-fidelity semantic-level reconstruction. As an image embedding in the language space, ViLex tokens leverage the compositionality of natural languages, allowing them to be used independently as "text tokens" or combined with natural language tokens to prompt pretrained T2I models with both visual and textual inputs, mirroring how we interact with vision-language models (VLMs). Experiments demonstrate that ViLex achieves higher fidelity in image reconstruction compared to text embeddings--even with a single ViLex token. Moreover, ViLex successfully performs various DreamBooth tasks in a zero-shot, unsupervised manner without fine-tuning T2I models. Additionally, ViLex serves as a powerful vision encoder, consistently improving vision-language model performance across 15 benchmarks relative to a strong SigLIP baseline.
Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence in expectation to the supervised squared loss in the case of Gaussian noise. However, its effectiveness with non-Gaussian noise remains unexplored. In this paper, we propose Generalized R2R (GR2R), extending the R2R framework to handle a broader class of noise distribution as additive noise like log-Rayleigh and address the natural exponential family including Poisson and Gamma noise distributions, which play a key role in many applications including low-photon imaging and synthetic aperture radar. We show that the GR2R loss is an unbiased estimator of the supervised loss and that the popular Stein's unbiased risk estimator can be seen as a special case. A series of experiments with Gaussian, Poisson, and Gamma noise validate GR2R's performance, showing its effectiveness compared to other self-supervised methods.
Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process. Instance-dependent label noise (IDN), where the probability of a label being corrupted depends on the input features, poses a significant challenge because it is more prevalent and harder to address than instance-independent noise. In this paper, we propose a novel hybrid framework that combines self-supervised learning using SimCLR with iterative pseudo-label refinement to mitigate the effects of IDN. The self-supervised pre-training phase enables the model to learn robust feature representations without relying on potentially noisy labels, establishing a noise-agnostic foundation. Subsequently, we employ an iterative training process with pseudo-label refinement, where confidently predicted samples are identified through a multistage approach and their labels are updated to improve label quality progressively. We evaluate our method on the CIFAR-10 and CIFAR-100 datasets augmented with synthetic instance-dependent noise at varying noise levels. Experimental results demonstrate that our approach significantly outperforms several state-of-the-art methods, particularly under high noise conditions, achieving notable improvements in classification accuracy and robustness. Our findings suggest that integrating self-supervised learning with iterative pseudo-label refinement offers an effective strategy for training deep neural networks on noisy datasets afflicted by instance-dependent label noise.
Hyperspectral and Multispectral Image Fusion (HMIF) aims to fuse low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) to reconstruct high spatial and high spectral resolution images. Current methods typically apply direct fusion from the two modalities without effective supervision, leading to an incomplete perception of deep modality-complementary information and a limited understanding of inter-modality correlations. To address these issues, we propose a simple yet effective solution for unsupervised HMIF, revealing that modality decoupling is key to improving fusion performance. Specifically, we propose an end-to-end self-supervised \textbf{Mo}dality-Decoupled \textbf{S}patial-\textbf{S}pectral Fusion (\textbf{MossFuse}) framework that decouples shared and complementary information across modalities and aggregates a concise representation of both LR-HSIs and HR-MSIs to reduce modality redundancy. Also, we introduce the subspace clustering loss as a clear guide to decouple modality-shared features from modality-complementary ones. Systematic experiments over multiple datasets demonstrate that our simple and effective approach consistently outperforms the existing HMIF methods while requiring considerably fewer parameters with reduced inference time. The anonymous source code is in \href{https://github.com/dusongcheng/MossFuse}{MossFuse}.
We study the problem of generating temporal object intrinsics -- temporally evolving sequences of object geometry, reflectance, and texture, such as a blooming rose -- from pre-trained 2D foundation models. Unlike conventional 3D modeling and animation techniques that require extensive manual effort and expertise, we introduce a method that generates such assets with signals distilled from pre-trained 2D diffusion models. To ensure the temporal consistency of object intrinsics, we propose Neural Templates for temporal-state-guided distillation, derived automatically from image features from self-supervised learning. Our method can generate high-quality temporal object intrinsics for several natural phenomena and enable the sampling and controllable rendering of these dynamic objects from any viewpoint, under any environmental lighting conditions, at any time of their lifespan. Project website: https://chen-geng.com/rose4d
Structural health monitoring (SHM) has experienced significant advancements in recent decades, accumulating massive monitoring data. Data anomalies inevitably exist in monitoring data, posing significant challenges to their effective utilization. Recently, deep learning has emerged as an efficient and effective approach for anomaly detection in bridge SHM. Despite its progress, many deep learning models require large amounts of labeled data for training. The process of labeling data, however, is labor-intensive, time-consuming, and often impractical for large-scale SHM datasets. To address these challenges, this work explores the use of self-supervised learning (SSL), an emerging paradigm that combines unsupervised pre-training and supervised fine-tuning. The SSL-based framework aims to learn from only a very small quantity of labeled data by fine-tuning, while making the best use of the vast amount of unlabeled SHM data by pre-training. Mainstream SSL methods are compared and validated on the SHM data of two in-service bridges. Comparative analysis demonstrates that SSL techniques boost data anomaly detection performance, achieving increased F1 scores compared to conventional supervised training, especially given a very limited amount of labeled data. This work manifests the effectiveness and superiority of SSL techniques on large-scale SHM data, providing an efficient tool for preliminary anomaly detection with scarce label information.
We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from earlier layers, making the SSL model aware of the current language and speaker context. This approach reduces the reliance on input audio features while preserving the integrity of the base SSLR. CA-SSLR improves the model's capabilities and demonstrates its generality on unseen tasks with minimal task-specific tuning. Our method employs linear modulation to dynamically adjust internal representations, enabling fine-grained adaptability without significantly altering the original model behavior. Experiments show that CA-SSLR reduces the number of trainable parameters, mitigates overfitting, and excels in under-resourced and unseen tasks. Specifically, CA-SSLR achieves a 10% relative reduction in LID errors, a 37% improvement in ASR CER on the ML-SUPERB benchmark, and a 27% decrease in SV EER on VoxCeleb-1, demonstrating its effectiveness.
Graph Neural Networks (GNNs) have demonstrated their effectiveness in various graph learning tasks, yet their reliance on neighborhood aggregation during inference poses challenges for deployment in latency-sensitive applications, such as real-time financial fraud detection. To address this limitation, recent studies have proposed distilling knowledge from teacher GNNs into student Multi-Layer Perceptrons (MLPs) trained on node content, aiming to accelerate inference. However, these approaches often inadequately explore structural information when inferring unseen nodes. To this end, we introduce SimMLP, a Self-supervised framework for learning MLPs on graphs, designed to fully integrate rich structural information into MLPs. Notably, SimMLP is the first MLP-learning method that can achieve equivalence to GNNs in the optimal case. The key idea is to employ self-supervised learning to align the representations encoded by graph context-aware GNNs and neighborhood dependency-free MLPs, thereby fully integrating the structural information into MLPs. We provide a comprehensive theoretical analysis, demonstrating the equivalence between SimMLP and GNNs based on mutual information and inductive bias, highlighting SimMLP's advanced structural learning capabilities. Additionally, we conduct extensive experiments on 20 benchmark datasets, covering node classification, link prediction, and graph classification, to showcase SimMLP's superiority over state-of-the-art baselines, particularly in scenarios involving unseen nodes (e.g., inductive and cold-start node classification) where structural insights are crucial. Our codes are available at: https://github.com/Zehong-Wang/SimMLP.
We examine the text-free speech representations of raw audio obtained from a self-supervised learning (SSL) model by analyzing the synthesized speech using the SSL representations instead of conventional text representations. Since raw audio does not have paired speech representations as transcribed texts do, obtaining speech representations from unpaired speech is crucial for augmenting available datasets for speech synthesis. Specifically, the proposed speech synthesis is conducted using discrete symbol representations from the SSL model in comparison with text representations, and analytical examinations of the synthesized speech have been carried out. The results empirically show that using text representations is advantageous for preserving semantic information, while using discrete symbol representations is superior for preserving acoustic content, including prosodic and intonational information.
Augmentation-based self-supervised learning methods have shown remarkable success in self-supervised visual representation learning, excelling in learning invariant features but often neglecting equivariant ones. This limitation reduces the generalizability of foundation models, particularly for downstream tasks requiring equivariance. We propose integrating an image reconstruction task as an auxiliary component in augmentation-based self-supervised learning algorithms to facilitate equivariant feature learning without additional parameters. Our method implements a cross-attention mechanism to blend features learned from two augmented views, subsequently reconstructing one of them. This approach is adaptable to various datasets and augmented-pair based learning methods. We evaluate its effectiveness on learning equivariant features through multiple linear regression tasks and downstream applications on both artificial (3DIEBench) and natural (ImageNet) datasets. Results consistently demonstrate significant improvements over standard augmentation-based self-supervised learning methods and state-of-the-art approaches, particularly excelling in scenarios involving combined augmentations. Our method enhances the learning of both invariant and equivariant features, leading to more robust and generalizable visual representations for computer vision tasks.
Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typically inferior to competing approaches. Most users cannot afford fine-tuning due to the need for large amounts of data, high GPU consumption, and specialized user knowledge. Therefore, the practical use of MIM representations is limited. In this paper we ask what is the reason for the poor out-of-the-box performance of MIMs. Is it due to weaker features produced by MIM models, or is it due to suboptimal usage? Through detailed analysis, we show that attention in MIMs is spread almost uniformly over many patches, leading to ineffective aggregation by the [cls] token. Based on this insight, we propose Selective Aggregation to better capture the rich semantic information retained in patch tokens, which significantly improves the out-of-the-box performance of MIM.
Self-supervised learning (SSL) frameworks consist of pretext task, and loss function aiming to learn useful general features from unlabeled data. The basic idea of most SSL baselines revolves around enforcing the invariance to a variety of data augmentations via the loss function. However, one main issue is that, inattentive or deterministic enforcement of the invariance to any kind of data augmentation is generally not only inefficient, but also potentially detrimental to performance on the downstream tasks. In this work, we investigate the issue from the viewpoint of uncertainty in invariance representation. Uncertainty representation is fairly under-explored in the design of SSL architectures as well as loss functions. We incorporate uncertainty representation in both loss function as well as architecture design aiming for more data-dependent invariance enforcement. The former is represented in the form of data-derived uncertainty in SSL loss function resulting in a generative-discriminative loss function. The latter is achieved by feeding slightly different distorted versions of samples to the ensemble aiming for learning better and more robust representation. Specifically, building upon the recent methods that use hard and soft whitening (a.k.a redundancy reduction), we introduce a new approach GUESS, a pseudo-whitening framework, composed of controlled uncertainty injection, a new architecture, and a new loss function. We include detailed results and ablation analysis establishing GUESS as a new baseline.
Masked Autoencoders (MAEs) are an important divide in self-supervised learning (SSL) due to their independence from augmentation techniques for generating positive (and/or negative) pairs as in contrastive frameworks. Their masking and reconstruction strategy also nicely aligns with SSL approaches in natural language processing. Most MAEs are built upon Transformer-based architectures where visual features are not regularized as opposed to their convolutional neural network (CNN) based counterparts, which can potentially hinder their performance. To address this, we introduce MAGMA, a novel batch-wide layer-wise regularization loss applied to representations of different Transformer layers. We demonstrate that by plugging in the proposed regularization loss, one can significantly improve the performance of MAE-based models. We further demonstrate the impact of the proposed loss on optimizing other generic SSL approaches (such as VICReg and SimCLR), broadening the impact of the proposed approach. Our code base can be found at https://github.com/adondera/magma.