Related papers: Encoding the Subsurface in 3D with Seismic
Masked Autoencoders (MAEs) have emerged as a powerful pretraining technique for vision foundation models. Despite their effectiveness, they require extensive hyperparameter tuning (masking ratio, patch size, encoder/decoder layers) when…
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…
In this work, we focus on unsupervised vision-language-action mapping in the area of robotic manipulation. Recently, multiple approaches employing pre-trained large language and vision models have been proposed for this task. However, they…
Side-scan sonar (SSS) imagery presents unique challenges in the classification of man-made objects on the seafloor due to the complex and varied underwater environments. Historically, experts have manually interpreted SSS images, relying on…
A central goal in understanding human vision is to uncover the visual features that drive neuronal activity. A growing body of work has used artificial neural networks as encoding models to predict cortical responses to natural images,…
With the development of generative-based self-supervised learning (SSL) approaches like BeiT and MAE, how to learn good representations by masking random patches of the input image and reconstructing the missing information has grown in…
Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and disaster response. However, existing methods rely on…
Accurate atmospheric profiles from remote sensing instruments such as Doppler Lidar, Radar, and radiometers are frequently corrupted by low-SNR (Signal to Noise Ratio) gates, range folding, and spurious discontinuities. Traditional gap…
In this paper, we propose a new self-supervised method, which is called Denoising Masked AutoEncoders (DMAE), for learning certified robust classifiers of images. In DMAE, we corrupt each image by adding Gaussian noises to each pixel value…
Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…
Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train…
Underground mining disasters produce pervasive darkness, dust, and collapses that obscure vision and make situational awareness difficult for humans and conventional systems. To address this, we propose MDSE, Multimodal Disaster Situation…
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…
The volume of unlabelled Earth observation (EO) data is huge, but many important applications lack labelled training data. However, EO data offers the unique opportunity to pair data from different modalities and sensors automatically based…
Recently, significant progress has been made in masked image modeling to catch up to masked language modeling. However, unlike words in NLP, the lack of semantic decomposition of images still makes masked autoencoding (MAE) different…
Scalable general-purpose representations of the built environment are crucial for geospatial artificial intelligence applications. This paper introduces S2Vec, a novel self-supervised framework for learning such geospatial embeddings. S2Vec…
Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…
Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…
Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language.…
Machine learning-based seismic processing models are typically trained separately to perform specific seismic processing tasks (SPTs), and as a result, require plenty of training data. However, preparing training data sets is not trivial,…