Galileo: Learning Global and Local Features in Pretrained Remote Sensing Models

From crop mapping to flood detection, machine learning in remote sensing has a wide range of societally beneficial applications. The commonalities between remote sensing data in these applications present an opportunity for pretrained machine learning models tailored to remote sensing to reduce the labeled data and effort required to solve individual tasks. However, such models must be: (i) flexible enough to ingest input data of varying sensor modalities and shapes (i.e., of varying spatial and temporal dimensions), and (ii) able to model Earth surface phenomena of varying scales and types. To solve this gap, we present Galileo, a family of pretrained remote sensing models designed to flexibly process multimodal remote sensing data. We also introduce a novel and highly effective self-supervised learning approach to learn both large- and small-scale features, a challenge not addressed by previous models. Our Galileo models obtain state-of-the-art results across diverse remote sensing tasks.

LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate

High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without finetuning -- ViTs poorly extrapolate to more patches at test time, although transformers offer sequence length flexibility. We attribute this shortcoming to the current patch position encoding methods, which create a distribution shift when extrapolating. We propose a drop-in replacement for the position encoding of plain ViTs that restricts attention heads to fixed fields of view, pointed in different directions, using 2D attention masks. Our novel method, called LookHere, provides translation-equivariance, ensures attention head diversity, and limits the distribution shift that attention heads face when extrapolating. We demonstrate that LookHere improves performance on classification (avg. 1.6%), against adversarial attack (avg. 5.4%), and decreases calibration error (avg. 1.5%) -- on ImageNet without extrapolation. With extrapolation, LookHere outperforms the current SoTA position encoding method, 2D-RoPE, by 21.7% on ImageNet when trained at $224^2$ px and tested at $1024^2$ px. Additionally, we release a high-resolution test set to improve the evaluation of high-resolution image classifiers, called ImageNet-HR.

CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders

A vital and rapidly growing application, remote sensing offers vast yet sparsely labeled, spatially aligned multimodal data; this makes self-supervised learning algorithms invaluable. We present CROMA: a framework that combines contrastive and reconstruction self-supervised objectives to learn rich unimodal and multimodal representations. Our method separately encodes masked-out multispectral optical and synthetic aperture radar samples -- aligned in space and time -- and performs cross-modal contrastive learning. Another encoder fuses these sensors, producing joint multimodal encodings that are used to predict the masked patches via a lightweight decoder. We show that these objectives are complementary when leveraged on spatially aligned multimodal data. We also introduce X- and 2D-ALiBi, which spatially biases our cross- and self-attention matrices. These strategies improve representations and allow our models to effectively extrapolate to images up to 17.6x larger at test-time. CROMA outperforms the current SoTA multispectral model, evaluated on: four classification benchmarks -- finetuning (avg. 1.8%), linear (avg. 2.4%) and nonlinear (avg. 1.4%) probing, kNN classification (avg. 3.5%), and K-means clustering (avg. 8.4%); and three segmentation benchmarks (avg. 6.4%). CROMA's rich, optionally multimodal representations can be widely leveraged across remote sensing applications.

Under the Cover Infant Pose Estimation using Multimodal Data

Infant pose monitoring during sleep has multiple applications in both healthcare and home settings. In a healthcare setting, pose detection can be used for region of interest detection and movement detection for noncontact based monitoring systems. In a home setting, pose detection can be used to detect sleep positions which has shown to have a strong influence on multiple health factors. However, pose monitoring during sleep is challenging due to heavy occlusions from blanket coverings and low lighting. To address this, we present a novel dataset, Simultaneously-collected multimodal Mannequin Lying pose (SMaL) dataset, for under the cover infant pose estimation. We collect depth and pressure imagery of an infant mannequin in different poses under various cover conditions. We successfully infer full body pose under the cover by training state-of-art pose estimation methods and leveraging existing multimodal adult pose datasets for transfer learning. We demonstrate a hierarchical pretraining strategy for transformer-based models to significantly improve performance on our dataset. Our best performing model was able to detect joints under the cover within 25mm 86% of the time with an overall mean error of 16.9mm. Data, code and models publicly available at https://github.com/DanielKyr/SMaL

Transfer Learning with Pretrained Remote Sensing Transformers

Although the remote sensing (RS) community has begun to pretrain transformers (intended to be fine-tuned on RS tasks), it is unclear how these models perform under distribution shifts. Here, we pretrain a new RS transformer--called SatViT-V2--on 1.3 million satellite-derived RS images, then fine-tune it (along with five other models) to investigate how it performs on distributions not seen during training. We split an expertly labeled land cover dataset into 14 datasets based on source biome. We train each model on each biome separately and test them on all other biomes. In all, this amounts to 1638 biome transfer experiments. After fine-tuning, we find that SatViT-V2 outperforms SatViT-V1 by 3.1% on in-distribution (matching biomes) and 2.8% on out-of-distribution (mismatching biomes) data. Additionally, we find that initializing fine-tuning from the linear probed solution (i.e., leveraging LPFT [1]) improves SatViT-V2's performance by another 1.2% on in-distribution and 2.4% on out-of-distribution data. Next, we find that pretrained RS transformers are better calibrated under distribution shifts than non-pretrained models and leveraging LPFT results in further improvements in model calibration. Lastly, we find that five measures of distribution shift are moderately correlated with biome transfer performance. We share code and pretrained model weights. (https://github.com/antofuller/SatViT)

Audiogram Digitization Tool for Audiological Reports

A number of private and public insurers compensate workers whose hearing loss can be directly attributed to excessive exposure to noise in the workplace. The claim assessment process is typically lengthy and requires significant effort from human adjudicators who must interpret hand-recorded audiograms, often sent via fax or equivalent. In this work, we present a solution developed in partnership with the Workplace Safety Insurance Board of Ontario to streamline the adjudication process. In particular, we present the first audiogram digitization algorithm capable of automatically extracting the hearing thresholds from a scanned or faxed audiology report as a proof-of-concept. The algorithm extracts most thresholds within 5 dB accuracy, allowing to substantially lessen the time required to convert an audiogram into digital format in a semi-supervised fashion, and is a first step towards the automation of the adjudication process. The source code for the digitization algorithm and a desktop-based implementation of our NIHL annotation portal is publicly available on GitHub (https://github.com/GreenCUBIC/AudiogramDigitization).