Subash Khanal

Subash Khanal, Srikumar Sastry, Aayush Dhakal et al.

We focus on the task of soundscape mapping, which involves predicting the most probable sounds that could be perceived at a particular geographic location. We utilise recent state-of-the-art models to encode geotagged audio, a textual description of the audio, and an overhead image of its capture location using contrastive pre-training. The end result is a shared embedding space for the three modalities, which enables the construction of soundscape maps for any geographic region from textual or audio queries. Using the SoundingEarth dataset, we find that our approach significantly outperforms the existing SOTA, with an improvement of image-to-audio Recall@100 from 0.256 to 0.450. Our code is available at https://github.com/mvrl/geoclap.

Aayush Dhakal, Adeel Ahmad, Subash Khanal et al.

We propose a weakly supervised approach for creating maps using free-form textual descriptions. We refer to this work of creating textual maps as zero-shot mapping. Prior works have approached mapping tasks by developing models that predict a fixed set of attributes using overhead imagery. However, these models are very restrictive as they can only solve highly specific tasks for which they were trained. Mapping text, on the other hand, allows us to solve a large variety of mapping problems with minimal restrictions. To achieve this, we train a contrastive learning framework called Sat2Cap on a new large-scale dataset with 6.1M pairs of overhead and ground-level images. For a given location and overhead image, our model predicts the expected CLIP embeddings of the ground-level scenery. The predicted CLIP embeddings are then used to learn about the textual space associated with that location. Sat2Cap is also conditioned on date-time information, allowing it to model temporally varying concepts over a location. Our experimental results demonstrate that our models successfully capture ground-level concepts and allow large-scale mapping of fine-grained textual queries. Our approach does not require any text-labeled data, making the training easily scalable. The code, dataset, and models will be made publicly available.

Subash Khanal, Eric Xing, Srikumar Sastry et al.

A soundscape is defined by the acoustic environment a person perceives at a location. In this work, we propose a framework for mapping soundscapes across the Earth. Since soundscapes involve sound distributions that span varying spatial scales, we represent locations with multi-scale satellite imagery and learn a joint representation among this imagery, audio, and text. To capture the inherent uncertainty in the soundscape of a location, we design the representation space to be probabilistic. We also fuse ubiquitous metadata (including geolocation, time, and data source) to enable learning of spatially and temporally dynamic representations of soundscapes. We demonstrate the utility of our framework by creating large-scale soundscape maps integrating both audio and text with temporal control. To facilitate future research on this task, we also introduce a large-scale dataset, GeoSound, containing over $300k$ geotagged audio samples paired with both low- and high-resolution satellite imagery. We demonstrate that our method outperforms the existing state-of-the-art on both GeoSound and the existing SoundingEarth dataset. Our dataset and code is available at https://github.com/mvrl/PSM.

Srikumar Sastry, Subash Khanal, Aayush Dhakal et al.

We introduce ProM3E, a probabilistic masked multimodal embedding model for any-to-any generation of multimodal representations for ecology. ProM3E is based on masked modality reconstruction in the embedding space, learning to infer missing modalities given a few context modalities. By design, our model supports modality inversion in the embedding space. The probabilistic nature of our model allows us to analyse the feasibility of fusing various modalities for given downstream tasks, essentially learning what to fuse. Using these features of our model, we propose a novel cross-modal retrieval approach that mixes inter-modal and intra-modal similarities to achieve superior performance across all retrieval tasks. We further leverage the hidden representation from our model to perform linear probing tasks and demonstrate the superior representation learning capability of our model. All our code, datasets and model will be released at https://vishu26.github.io/prom3e.

Zhexiao Xiong, Xin Xing, Scott Workman et al.

We introduce the task of mixed-view panorama synthesis, where the goal is to synthesize a novel panorama given a small set of input panoramas and a satellite image of the area. This contrasts with previous work which only uses input panoramas (same-view synthesis), or an input satellite image (cross-view synthesis). We argue that the mixed-view setting is the most natural to support panorama synthesis for arbitrary locations worldwide. A critical challenge is that the spatial coverage of panoramas is uneven, with few panoramas available in many regions of the world. We introduce an approach that utilizes diffusion-based modeling and an attention-based architecture for extracting information from all available input imagery. Experimental results demonstrate the effectiveness of our proposed method. In particular, our model can handle scenarios when the available panoramas are sparse or far from the location of the panorama we are attempting to synthesize. The project page is available at https://mixed-view.github.io

Srikumar Sastry, Subash Khanal, Aayush Dhakal et al.

We present TaxaBind, a unified embedding space for characterizing any species of interest. TaxaBind is a multimodal embedding space across six modalities: ground-level images of species, geographic location, satellite image, text, audio, and environmental features, useful for solving ecological problems. To learn this joint embedding space, we leverage ground-level images of species as a binding modality. We propose multimodal patching, a technique for effectively distilling the knowledge from various modalities into the binding modality. We construct two large datasets for pretraining: iSatNat with species images and satellite images, and iSoundNat with species images and audio. Additionally, we introduce TaxaBench-8k, a diverse multimodal dataset with six paired modalities for evaluating deep learning models on ecological tasks. Experiments with TaxaBind demonstrate its strong zero-shot and emergent capabilities on a range of tasks including species classification, cross-model retrieval, and audio classification. The datasets and models are made available at https://github.com/mvrl/TaxaBind.

Srikumar Sastry, Subash Khanal, Aayush Dhakal et al.

We present GeoSynth, a model for synthesizing satellite images with global style and image-driven layout control. The global style control is via textual prompts or geographic location. These enable the specification of scene semantics or regional appearance respectively, and can be used together. We train our model on a large dataset of paired satellite imagery, with automatically generated captions, and OpenStreetMap data. We evaluate various combinations of control inputs, including different types of layout controls. Results demonstrate that our model can generate diverse, high-quality images and exhibits excellent zero-shot generalization. The code and model checkpoints are available at https://github.com/mvrl/GeoSynth.

Aayush Dhakal, Srikumar Sastry, Subash Khanal et al.

The choice of representation for geographic location significantly impacts the accuracy of models for a broad range of geospatial tasks, including fine-grained species classification, population density estimation, and biome classification. Recent works like SatCLIP and GeoCLIP learn such representations by contrastively aligning geolocation with co-located images. While these methods work exceptionally well, in this paper, we posit that the current training strategies fail to fully capture the important visual features. We provide an information-theoretic perspective on why the resulting embeddings from these methods discard crucial visual information that is important for many downstream tasks. To solve this problem, we propose a novel retrieval-augmented strategy called RANGE. We build our method on the intuition that the visual features of a location can be estimated by combining the visual features from multiple similar-looking locations. We evaluate our method across a wide variety of tasks. Our results show that RANGE outperforms the existing state-of-the-art models with significant margins in most tasks. We show gains of up to 13.1% on classification tasks and 0.145 $R^2$ on regression tasks. All our code and models will be made available at: https://github.com/mvrl/RANGE.

Srikumar Sastry, Aayush Dhakal, Eric Xing et al.

Learning the hierarchical structure of data in vision-language models is a significant challenge. Previous works have attempted to address this challenge by employing entailment learning. However, these approaches fail to model the transitive nature of entailment explicitly, which establishes the relationship between order and semantics within a representation space. In this work, we introduce Radial Cross-Modal Embeddings (RCME), a framework that enables the explicit modeling of transitivity-enforced entailment. Our proposed framework optimizes for the partial order of concepts within vision-language models. By leveraging our framework, we develop a hierarchical vision-language foundation model capable of representing the hierarchy in the Tree of Life. Our experiments on hierarchical species classification and hierarchical retrieval tasks demonstrate the enhanced performance of our models compared to the existing state-of-the-art models. Our code and models are open-sourced at https://vishu26.github.io/RCME/index.html.

Subash Khanal, Srikumar Sastry, Aayush Dhakal et al.

We present Sat2Sound, a multimodal representation learning framework for soundscape mapping, designed to predict the distribution of sounds at any location on Earth. Existing methods for this task rely on satellite image and paired geotagged audio samples, which often fail to capture the diversity of sound sources at a given location. To address this limitation, we enhance existing datasets by leveraging a Vision-Language Model (VLM) to generate semantically rich soundscape descriptions for locations depicted in satellite images. Our approach incorporates contrastive learning across audio, audio captions, satellite images, and satellite image captions. We hypothesize that there is a fixed set of soundscape concepts shared across modalities. To this end, we learn a shared codebook of soundscape concepts and represent each sample as a weighted average of these concepts. Sat2Sound achieves state-of-the-art performance in cross-modal retrieval between satellite image and audio on two datasets: GeoSound and SoundingEarth. Additionally, building on Sat2Sound's ability to retrieve detailed soundscape captions, we introduce a novel application: location-based soundscape synthesis, which enables immersive acoustic experiences. Our code and models will be publicly available.

Srikumar Sastry, Xin Xing, Aayush Dhakal et al.

We focus on species distribution modeling using global-scale presence-only data, leveraging geographical and environmental features to map species ranges, as in previous studies. However, we innovate by integrating taxonomic classification into our approach. Specifically, we propose using a large language model to extract a latent representation of the taxonomic classification from a textual prompt. This allows us to map the range of any taxonomic rank, including unseen species, without additional supervision. We also present a new proximity-aware evaluation metric, suitable for evaluating species distribution models, which addresses critical shortcomings of traditional metrics. We evaluated our model for species range prediction, zero-shot prediction, and geo-feature regression and found that it outperforms several state-of-the-art models.

Aayush Dhakal, Subash Khanal, Srikumar Sastry et al.

In remote sensing, we are interested in modeling various modalities for some geographic location. Several works have focused on learning the relationship between a location and type of landscape, habitability, audio, textual descriptions, etc. Recently, a common way to approach these problems is to train a deep-learning model that uses satellite images to infer some unique characteristics of the location. In this work, we present a deep-learning model, GeoBind, that can infer about multiple modalities, specifically text, image, and audio, from satellite imagery of a location. To do this, we use satellite images as the binding element and contrastively align all other modalities to the satellite image data. Our training results in a joint embedding space with multiple types of data: satellite image, ground-level image, audio, and text. Furthermore, our approach does not require a single complex dataset that contains all the modalities mentioned above. Rather it only requires multiple satellite-image paired data. While we only align three modalities in this paper, we present a general framework that can be used to create an embedding space with any number of modalities by using satellite images as the binding element. Our results show that, unlike traditional unimodal models, GeoBind is versatile and can reason about multiple modalities for a given satellite image input.