Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Today's most advanced multimodal models remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good performance, effectively distilling these closed models into open ones. As a result, the community is still missing foundational knowledge about how to build performant VLMs from scratch. We present Molmo, a new family of VLMs that are state-of-the-art in their class of openness. Our key innovation is a novel, highly detailed image caption dataset collected entirely from human annotators using speech-based descriptions. To enable a wide array of user interactions, we also introduce a diverse dataset mixture for fine-tuning that includes in-the-wild Q&A and innovative 2D pointing data. The success of our approach relies on careful choices for the model architecture details, a well-tuned training pipeline, and, most critically, the quality of our newly collected datasets, all of which will be released. The best-in-class 72B model within the Molmo family not only outperforms others in the class of open weight and data models but also compares favorably against proprietary systems like GPT-4o, Claude 3.5, and Gemini 1.5 on both academic benchmarks and human evaluation. We will be releasing all of our model weights, captioning and fine-tuning data, and source code in the near future. Select model weights, inference code, and demo are available at https://molmo.allenai.org.

On the Generalizability of Foundation Models for Crop Type Mapping

Foundation models pre-trained using self-supervised and weakly-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text generation, and image recognition. Recently, the Earth observation (EO) field has produced several foundation models pre-trained directly on multispectral satellite imagery (e.g., Sentinel-2) for applications like precision agriculture, wildfire and drought monitoring, and natural disaster response. However, few studies have investigated the ability of these models to generalize to new geographic locations, and potential concerns of geospatial bias -- models trained on data-rich developed countries not transferring well to data-scarce developing countries -- remain. We investigate the ability of popular EO foundation models to transfer to new geographic regions in the agricultural domain, where differences in farming practices and class imbalance make transfer learning particularly challenging. We first select six crop classification datasets across five continents, normalizing for dataset size and harmonizing classes to focus on four major cereal grains: maize, soybean, rice, and wheat. We then compare three popular foundation models, pre-trained on SSL4EO-S12, SatlasPretrain, and ImageNet, using in-distribution (ID) and out-of-distribution (OOD) evaluation. Experiments show that pre-trained weights designed explicitly for Sentinel-2, such as SSL4EO-S12, outperform general pre-trained weights like ImageNet. Furthermore, the benefits of pre-training on OOD data are the most significant when only 10--100 ID training samples are used. Transfer learning and pre-training with OOD and limited ID data show promising applications, as many developing regions have scarce crop type labels. All harmonized datasets and experimental code are open-source and available for download.

Satellite Imagery and AI: A New Era in Ocean Conservation, from Research to Deployment and Impact

Illegal, unreported, and unregulated (IUU) fishing poses a global threat to ocean habitats. Publicly available satellite data offered by NASA and the European Space Agency (ESA) provide an opportunity to actively monitor this activity. Effectively leveraging satellite data for maritime conservation requires highly reliable machine learning models operating globally with minimal latency. This paper introduces three specialized computer vision models designed for synthetic aperture radar (Sentinel-1), optical imagery (Sentinel-2), and nighttime lights (Suomi-NPP/NOAA-20). It also presents best practices for developing and delivering real-time computer vision services for conservation. These models have been deployed in Skylight, a real time maritime monitoring platform, which is provided at no cost to users worldwide.

Zooming Out on Zooming In: Advancing Super-Resolution for Remote Sensing

Super-Resolution for remote sensing has the potential for huge impact on planet monitoring by producing accurate and realistic high resolution imagery on a frequent basis and a global scale. Despite a lot of attention, several inconsistencies and challenges have prevented it from being deployed in practice. These include the lack of effective metrics, fragmented and relatively small-scale datasets for training, insufficient comparisons across a suite of methods, and unclear evidence for the use of super-resolution outputs for machine consumption. This work presents a new metric for super-resolution, CLIPScore, that corresponds far better with human judgments than previous metrics on an extensive study. We use CLIPScore to evaluate four standard methods on a new large-scale dataset, S2-NAIP, and three existing benchmark datasets, and find that generative adversarial networks easily outperform more traditional L2 loss-based models and are more semantically accurate than modern diffusion models. We also find that using CLIPScore as an auxiliary loss can speed up the training of GANs by 18x and lead to improved outputs, resulting in an effective model in diverse geographies across the world which we will release publicly. The dataset, pre-trained model weights, and code are available at https://github.com/allenai/satlas-super-resolution/.

Satlas: A Large-Scale, Multi-Task Dataset for Remote Sensing Image Understanding

Remote sensing images are useful for a wide variety of environmental and earth monitoring tasks, including tracking deforestation, illegal fishing, urban expansion, and natural disasters. The earth is extremely diverse -- the amount of potential tasks in remote sensing images is massive, and the sizes of features range from several kilometers to just tens of centimeters. However, creating generalizable computer vision methods is a challenge in part due to the lack of a large-scale dataset that captures these diverse features for many tasks. In this paper, we present Satlas, a remote sensing dataset and benchmark that is large in both breadth, featuring all of the aforementioned applications and more, as well as scale, comprising 290M labels under 137 categories and seven label modalities. We evaluate eight baselines and a proposed method on Satlas, and find that there is substantial room for improvement in addressing research challenges specific to remote sensing, including processing image time series that consist of images from very different types of sensors, and taking advantage of long-range spatial context. We also find that pre-training on Satlas substantially improves performance on downstream tasks with few labeled examples, increasing average accuracy by 16% over ImageNet and 5% over the next best baseline.

Self-Supervised Multi-Object Tracking with Cross-Input Consistency

In this paper, we propose a self-supervised learning procedure for training a robust multi-object tracking (MOT) model given only unlabeled video. While several self-supervisory learning signals have been proposed in prior work on single-object tracking, such as color propagation and cycle-consistency, these signals cannot be directly applied for training RNN models, which are needed to achieve accurate MOT: they yield degenerate models that, for instance, always match new detections to tracks with the closest initial detections. We propose a novel self-supervisory signal that we call cross-input consistency: we construct two distinct inputs for the same sequence of video, by hiding different information about the sequence in each input. We then compute tracks in that sequence by applying an RNN model independently on each input, and train the model to produce consistent tracks across the two inputs. We evaluate our unsupervised method on MOT17 and KITTI -- remarkably, we find that, despite training only on unlabeled video, our unsupervised approach outperforms four supervised methods published in the last 1--2 years, including Tracktor++, FAMNet, GSM, and mmMOT.

Updating Street Maps using Changes Detected in Satellite Imagery

Accurately maintaining digital street maps is labor-intensive. To address this challenge, much work has studied automatically processing geospatial data sources such as GPS trajectories and satellite images to reduce the cost of maintaining digital maps. An end-to-end map update system would first process geospatial data sources to extract insights, and second leverage those insights to update and improve the map. However, prior work largely focuses on the first step of this pipeline: these map extraction methods infer road networks from scratch given geospatial data sources (in effect creating entirely new maps), but do not address the second step of leveraging this extracted information to update the existing digital map data. In this paper, we first explain why current map extraction techniques yield low accuracy when extended to update existing maps. We then propose a novel method that leverages the progression of satellite imagery over time to substantially improve accuracy. Our approach first compares satellite images captured at different times to identify portions of the physical road network that have visibly changed, and then updates the existing map accordingly. We show that our change-based approach reduces map update error rates four-fold.

Beyond Road Extraction: A Dataset for Map Update using Aerial Images

The increasing availability of satellite and aerial imagery has sparked substantial interest in automatically updating street maps by processing aerial images. Until now, the community has largely focused on road extraction, where road networks are inferred from scratch from an aerial image. However, given that relatively high-quality maps exist in most parts of the world, in practice, inference approaches must be applied to update existing maps rather than infer new ones. With recent road extraction methods showing high accuracy, we argue that it is time to transition to the more practical map update task, where an existing map is updated by adding, removing, and shifting roads, without introducing errors in parts of the existing map that remain up-to-date. In this paper, we develop a new dataset called MUNO21 for the map update task, and show that it poses several new and interesting research challenges. We evaluate several state-of-the-art road extraction methods on MUNO21, and find that substantial further improvements in accuracy will be needed to realize automatic map update.

TagMe: GPS-Assisted Automatic Object Annotation in Videos

Training high-accuracy object detection models requires large and diverse annotated datasets. However, creating these data-sets is time-consuming and expensive since it relies on human annotators. We design, implement, and evaluate TagMe, a new approach for automatic object annotation in videos that uses GPS data. When the GPS trace of an object is available, TagMe matches the object's motion from GPS trace and the pixels' motions in the video to find the pixels belonging to the object in the video and creates the bounding box annotations of the object. TagMe works using passive data collection and can continuously generate new object annotations from outdoor video streams without any human annotators. We evaluate TagMe on a dataset of 100 video clips. We show TagMe can produce high-quality object annotations in a fully-automatic and low-cost way. Compared with the traditional human-in-the-loop solution, TagMe can produce the same amount of annotations at a much lower cost, e.g., up to 110x.

Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding

Inferring road graphs from satellite imagery is a challenging computer vision task. Prior solutions fall into two categories: (1) pixel-wise segmentation-based approaches, which predict whether each pixel is on a road, and (2) graph-based approaches, which predict the road graph iteratively. We find that these two approaches have complementary strengths while suffering from their own inherent limitations. In this paper, we propose a new method, Sat2Graph, which combines the advantages of the two prior categories into a unified framework. The key idea in Sat2Graph is a novel encoding scheme, graph-tensor encoding (GTE), which encodes the road graph into a tensor representation. GTE makes it possible to train a simple, non-recurrent, supervised model to predict a rich set of features that capture the graph structure directly from an image. We evaluate Sat2Graph using two large datasets. We find that Sat2Graph surpasses prior methods on two widely used metrics, TOPO and APLS. Furthermore, whereas prior work only infers planar road graphs, our approach is capable of inferring stacked roads (e.g., overpasses), and does so robustly.