Related papers: SatBLIP: Context Understanding and Feature Identif…

Capitalizing on vast amount of image-text data, large-scale vision-language pre-training has demonstrated remarkable zero-shot capabilities and has been utilized in several applications. However, models trained on general everyday…

In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional…

State-of-the-art techniques in weakly-supervised semantic segmentation (WSSS) using image-level labels exhibit severe performance degradation on driving scene datasets such as Cityscapes. To address this challenge, we develop a new WSSS…

Vision-language models (VLMs) have shown significant promise in remote sensing applications, particularly for land-use and land-cover (LULC) mapping via zero-shot classification and retrieval. However, current approaches face several key…

Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and…

Interpreting remote sensing imagery enables numerous downstream applications ranging from land-use planning to deforestation monitoring. Robustly classifying this data is challenging due to the Earth's geographic diversity. While many…

Wildfires are a growing threat to ecosystems, human lives, and infrastructure, with their frequency and intensity rising due to climate change and human activities. Early detection is critical, yet satellite-based monitoring remains…

Vision-Language Pretraining (VLP) has achieved remarkable success across various downstream tasks, but such gains are largely driven by scaling up on training data. Yet, literature methods treat image-text pairs as isolated training…

Pretrained vision-language models (VLMs) such as CLIP excel in general multimodal comprehension but often struggle to capture nuanced, context-dependent visual cues. This makes it difficult to distinguish between similar-looking concepts…

This paper proposes Spatially-Weighted CLIP (SW-CLIP), a novel framework for street-view geo-localization that explicitly incorporates spatial autocorrelation into vision-language contrastive learning. Unlike conventional CLIP-based methods…

This work presents an approach for combining household demographic and living standards survey questions with features derived from satellite imagery to predict the poverty rate of a region. Our approach utilizes visual features obtained…

Few-shot adaptation of vision-language models (VLMs) like CLIP typically relies on learning textual prompts matched to global image embeddings. Recent works extend this paradigm by incorporating local image-text alignment to capture…

Achieving high-quality semantic segmentation predictions using only image-level labels enables a new level of real-world applicability. Although state-of-the-art networks deliver reliable predictions, the amount of handcrafted pixel-wise…

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization…

Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance…

Many studies have predicted SocioEconomic Position (SEP) for aggregated spatial units such as villages using satellite data, but SEP prediction at the household level and other sources of imagery have not been yet explored. We assembled a…

Recent vision-language models (VLMs) such as CLIP, OpenCLIP, EVA02-CLIP and SigLIP achieve strong zero-shot performance, but it is unclear how reliably they respond to controlled linguistic perturbations. We introduce Language-Guided…

Satellite imagery is being leveraged for many societally critical tasks across climate, economics, and public health. Yet, because of heterogeneity in landscapes (e.g. how a road looks in different places), models can show disparate…

Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban…

Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP-2) accuracy on basic directional relationships. For safe…