Related papers: AdaMAE: Adaptive Masking for Efficient Spatiotempo…

We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network augmented with a global memory that provides context information…

Distributed fiber-optic acoustic sensing (DAS) has emerged as a transformative approach for distributed vibration measurement with high spatial resolution and long measurement range while maintaining cost-efficiency. However, the…

Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model's sensitivity to its…

Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy. Notably, the…

Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoencoder (MVMAE), a self-supervised framework that leverages…

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…

Prior work using Masked Autoencoders (MAEs) typically relies on random patch masking based on the assumption that images have significant redundancies across different channels, allowing for the reconstruction of masked content using…

Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by…

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…

Variational AutoEncoders (VAE) employ deep learning models to learn a continuous latent z-space that is subjacent to a high-dimensional observed dataset. With that, many tasks are made possible, including face reconstruction and face…

Transformer-based architectures have become competitive across a variety of visual domains, most notably images and videos. While prior work studies these modalities in isolation, having a common architecture suggests that one can train a…

We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup. Our method consists of two distinct components, one of which focuses on…

Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer…

Masked image modeling (MIM) has become a popular strategy for self-supervised learning~(SSL) of visual representations with Vision Transformers. A representative MIM model, the masked auto-encoder (MAE), randomly masks a subset of image…

Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed…

Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of…

This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked…

In this work, we propose a disruptively frugal LiDAR perception dataflow that generates rather than senses parts of the environment that are either predictable based on the extensive training of the environment or have limited consequence…

We approached the goal of applying meta-learning to self-supervised masked autoencoders for spatiotemporal learning in three steps. Broadly, we seek to understand the impact of applying meta-learning to existing state-of-the-art…

Broadcast and media organizations increasingly rely on artificial intelligence to automate the labor-intensive processes of content indexing, tagging, and metadata generation. However, existing AI systems typically operate on a single…