James R. Green

Daniel G. Kyrollos, Anthony Fuller, Kim Greenwood et al.

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

Anthony Fuller, Koreen Millard, James R. Green

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)

Anthony Fuller, Koreen Millard, James R. Green

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.

François Charih, James R. Green

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).

Aziz Al-Najjar, Marzieh Amini, James R. Green et al.

Most learning-based camera-LiDAR calibration methods treat each camera-LiDAR pair independently, ignoring the rigid geometric coupling in multi-camera platforms. As a result, per-camera estimates may be individually accurate yet inconsistent at the system level. We present a two-stage framework for joint multi-camera LiDAR extrinsic calibration that combines learned pairwise matching with geometric refinement. First, CMRNext is applied independently to each camera to produce initial extrinsic estimates and dense 2D-3D correspondences. These predictions are then jointly refined through a multi-frame bundle adjustment with reprojection, per-camera prior, and relative-pose prior terms. This approach converts pairwise predictions into a globally consistent multi-camera calibration. Experiments on KITTI (in-domain for CMRNext) and Walkley (out-of-domain) datasets show improved per-camera accuracy and inter-camera consistency. On KITTI, the method achieves 0.89 cm translation error and 0.038 rotation error. On Walkley, it reduces translation error from 108.6 cm to 3.1 cm, highlighting the benefit of explicit multi-camera coupling when single-camera predictions are less reliable.

Kevin Dick, Daniel G. Kyrollos, James R. Green

Across many domains, real-world problems can be represented as a network. Nodes represent domain-specific elements and edges capture the relationship between elements. Leveraging high-performance computing and optimized link prediction algorithms, it is increasingly possible to evaluate every possible combination of nodal pairs enabling the generation of a comprehensive prediction matrix (CPM) that places an individual link prediction score in the context of all possible links involving either node (providing data-driven context). Historically, this contextual information has been ignored given exponentially growing problem sizes resulting in computational intractability; however, we demonstrate that expending high-performance compute resources to generate CPMs is a worthwhile investment given the improvement in predictive performance. In this work, we generalize for all pairwise link-prediction tasks our novel semi-supervised machine learning method, denoted Reciprocal Perspective (RP). We demonstrate that RP significantly improves link prediction accuracy by leveraging the wealth of information in a CPM. Context-based features are extracted from the CPM for use in a stacked classifier and we demonstrate that the application of RP in a cascade almost always results in significantly (p < 0.05) improved predictions. These results on RS-type problems suggest that RP is applicable to a broad range of link prediction problems.

Anthony Fuller, Yousef Yassin, Daniel G. Kyrollos et al.

We introduce a simple enhancement of vision transformers (ViTs) to improve accuracy while maintaining throughput. Our approach, Jumbo, creates a wider CLS token, which is split to match the patch token width before attention, processed with self-attention, and reassembled. After attention, Jumbo applies a dedicated, wider FFN to this token. Since there is only one Jumbo token, its cost is minimal, and because we share this FFN across layers, its parameter count is controlled. Jumbo significantly improves over ViT+Registers on ImageNet-1K and ImageNet-21K. These gains are largest at small sizes / high speeds, e.g., ViT-nano+Jumbo outperforms ViT-nano+Registers by 13%. In fact, our Jumbo models are so efficient that they outperform specialized compute-efficient models while preserving the architectural advantages of plain ViTs, such as support for token dropping and other modalities. Accordingly, we demonstrate that Jumbo excels in these two settings via masked autoencoding and on a suite of time series benchmarks. Code and weights available: https://github.com/antofuller/jumbo

Ali Salamatian, Anthony Fuller, Pritam Sarkar et al.

Transformers dominate video recognition. They split videos into tokens, and processing them has expensive superlinear computational cost. Yet videos are filled with redundancy, so we can question the need for this expense. We introduce LookWhen, a selector-extractor framework that factorizes video recognition into learning when, where, and what to compute. Our shallow selector gets a scaled-down video and quickly scores all tokens across space-time, while our deep extractor gets the top-K selected tokens to approximate full-video representations without actually processing all the tokens. A key challenge is defining effective supervision for selection and extraction. For selection pre-training, we introduce a score on representations that ranks tokens by uniqueness using a simple nearest-neighbor distance. For extraction pre-training, we distill both a video teacher and an image teacher, for which we normalize its frame-wise representations to learn what changes within videos. Through these strategies, our selector-extractor learns general and efficient representations for feature extraction or fine-tuning to a task. Through experiments on Kinetics-400, SSv2, Epic-Kitchens, Diving48, Jester, and Charades, we show that LookWhen achieves a better accuracy-computation trade-off than efficient models and upgraded baselines of similar size. LookWhen Pareto-dominates in accuracy-FLOPs on 9 of 12 cases (6 tasks x 2 settings) and roughly matches on 3. In accuracy-throughput, measuring time in practice, LookWhen is more efficient still at 6.7x faster than InternVideo2-B at equal accuracy.

Gabriel Tseng, Anthony Fuller, Marlena Reil et al.

We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and fast) to glaciers (thousands of pixels and slow). We present a novel self-supervised learning algorithm that extracts multi-scale features across a flexible set of input modalities through masked modeling. Our dual global and local contrastive losses differ in their targets (deep representations vs. shallow input projections) and masking strategies (structured vs. not). Our Galileo is a single generalist model that outperforms SoTA specialist models for satellite images and pixel time series across eleven benchmarks and multiple tasks.

Anthony Fuller, Daniel G. Kyrollos, Yousef Yassin et al.

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.

Anthony Fuller, James R. Green, Evan Shelhamer

Model soups are strange and strangely effective combinations of parameters. They take a model (the stock), fine-tune it into multiple models (the ingredients), and then mix their parameters back into one model (the soup) to improve predictions. While all known soups require supervised learning, and optimize the same loss on labeled data, our recipes for Self-\emph{Soup}ervision generalize soups to self-supervised learning (SSL). Our Self-Souping lets us flavor ingredients on new data sources, e.g. from unlabeled data from a task for transfer or from a shift for robustness. We show that Self-Souping on corrupted test data, then fine-tuning back on uncorrupted train data, boosts robustness by +3.5\% (ImageNet-C) and +7\% (LAION-C). Self-\emph{Soup}ervision also unlocks countless SSL algorithms to cook the diverse ingredients needed for more robust soups. We show for the first time that ingredients can differ in their SSL hyperparameters -- and more surprisingly, in their SSL algorithms. We cook soups of MAE, MoCoV3, and MMCR ingredients that are more accurate than any one single SSL ingredient.

François Charih, James R. Green, Kyle K. Biggar

Aberrant protein-protein interactions (PPIs) underpin a plethora of human diseases, and disruption of these harmful interactions constitute a compelling treatment avenue. Advances in computational approaches to PPI prediction have closely followed progress in deep learning and natural language processing. In this review, we outline the state-of the-art for sequence-based PPI prediction methods and explore their impact on target identification and drug discovery. We begin with an overview of commonly used training data sources and techniques used to curate these data to enhance the quality of the training set. Subsequently, we survey various PPI predictor types, including traditional similarity-based approaches, and deep learning-based approaches with a particular emphasis on the transformer architecture. Finally, we provide examples of PPI prediction in systems-level proteomics analyses, target identification, and design of therapeutic peptides and antibodies. We also take the opportunity to showcase the potential of PPI-aware drug discovery models in accelerating therapeutic development.

Anthony Fuller, Yousef Yassin, Junfeng Wen et al.

Vision transformers are ever larger, more accurate, and more expensive to compute. The expense is even more extreme at high resolution as the number of tokens grows quadratically with the image size. We turn to adaptive computation to cope with this cost by learning to predict where to compute. Our LookWhere method divides the computation between a low-resolution selector and a high-resolution extractor without ever processing the full high-resolution input. We jointly pretrain the selector and extractor without task supervision by distillation from a self-supervised teacher, in effect, learning where and what to compute simultaneously. Unlike prior token reduction methods, which pay to save by pruning already-computed tokens, and prior token selection methods, which require complex and expensive per-task optimization, LookWhere economically and accurately selects and extracts transferrable representations of images. We show that LookWhere excels at sparse recognition on high-resolution inputs (Traffic Signs), maintaining accuracy while reducing FLOPs by up to 34x and time by 6x. It also excels at standard recognition tasks that are global (ImageNet classification) or local (ADE20K segmentation), improving accuracy while reducing time by 1.36x.