Related papers: Scale-MAE: A Scale-Aware Masked Autoencoder for Mu…

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…

Large-scale supervised pretraining is rapidly reshaping 3D medical image segmentation. However, existing efforts focus primarily on increasing dataset size and overlook the question of whether the backbone network is an effective…

Generating semantic segmentation datasets has consistently been laborious and time-consuming, particularly in the context of large models or specialized domains(i.e. Medical Imaging or Remote Sensing). Specifically, large models necessitate…

Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change. Large scale, high resolution data derived from these sensors can be used to inform intervention and policy…

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn…

Masked Autoencoders (MAEs) have emerged as a dominant strategy for self-supervised representation learning in natural images, where models are pre-trained to reconstruct masked patches with a pixel-wise mean squared error (MSE) between…

Affective video facial analysis (AVFA) has emerged as a key research field for building emotion-aware intelligent systems, yet this field continues to suffer from limited data availability. In recent years, the self-supervised learning…

We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models. To this end, this paper presents masked decision…

Machine learning using transformers has shown great potential in medical imaging, but its real-world applicability remains limited due to the scarcity of annotated data. In this study, we propose a practical framework for the few-shot…

Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases…

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud…

The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal…

Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled data for training…

We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online feature as extra BERT…

Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical…

Accurate ocean mapping is essential for applications such as bathymetry estimation, seabed characterization, marine litter detection, and ecosystem monitoring. However, ocean remote sensing (RS) remains constrained by limited labeled data…

Learning compact and interpretable representations of data is a critical challenge in scientific image analysis. Here, we introduce Affinity-VAE, a generative model that enables us to impose our scientific intuition about the similarity of…

The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through…

Low-dose computed tomography (LDCT) reduces the X-ray radiation but compromises image quality with more noises and artifacts. A plethora of transformer models have been developed recently to improve LDCT image quality. However, the success…

Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs).…