Related papers: A Multi-Task Foundation Model for Wireless Channel…
Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result,…
While image data starts to enjoy the simple-but-effective self-supervised learning scheme built upon masking and self-reconstruction objective thanks to the introduction of tokenization procedure and vision transformer backbone,…
Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…
Weather forecasting is a long-standing computational challenge with direct societal and economic impacts. This task involves a large amount of continuous data collection and exhibits rich spatiotemporal dependencies over long periods,…
Learning representations that transfer well to diverse downstream tasks remains a central challenge in representation learning. Existing paradigms -- contrastive learning, self-supervised masking, and denoising auto-encoders -- balance this…
Hyperspectral imagery provides rich spectral detail but poses unique challenges because of its high dimensionality in both spatial and spectral domains. We propose \textit{HyperspectralMAE}, a Transformer-based foundation model for…
Masked Image Modeling has been one of the most popular self-supervised learning paradigms to learn representations from large-scale, unlabeled Earth Observation images. While incorporating multi-modal and multi-temporal Earth Observation…
Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…
Meta-learning algorithms adapt quickly to new tasks that are drawn from the same task distribution as the training tasks. The mechanism leading to fast adaptation is the conditioning of a downstream predictive model on the inferred…
Artificial intelligence is a key enabler for next-generation wireless communication and sensing. Yet, today's learning-based wireless techniques do not generalize well: most models are task-specific, environment-dependent, and limited to…
We propose WirelessJEPA, a novel wireless foundation model (WFM) that uses the Joint Embedding Predictive Architecture (JEPA). WirelessJEPA learns general-purpose representations directly from real-world multi-antenna IQ data by predicting…
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy…
With the exponential growth of multimedia data, leveraging multimodal sensors presents a promising approach for improving accuracy in human activity recognition. Nevertheless, accurately identifying these activities using both video data…
For graph self-supervised learning (GSSL), masked autoencoder (MAE) follows the generative paradigm and learns to reconstruct masked graph edges or node features. Contrastive Learning (CL) maximizes the similarity between augmented views of…
Masked reconstruction serves as a fundamental pretext task for self-supervised learning, enabling the model to enhance its feature extraction capabilities by reconstructing the masked segments from extensive unlabeled data. In human…
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…
Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…
Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks. By comparison, vision foundation models (VFMs) often exhibit uneven improvements across…
The integration of different imaging modalities, such as structural, diffusion tensor, and functional magnetic resonance imaging, with deep learning models has yielded promising outcomes in discerning phenotypic characteristics and…
Human social behaviors are inherently multimodal necessitating the development of powerful audiovisual models for their perception. In this paper, we present Social-MAE, our pre-trained audiovisual Masked Autoencoder based on an extended…