Related papers: A large-scale image-text dataset benchmark for far…

Supervised learning demands large amounts of precisely annotated data to achieve promising results. Such data curation is labor-intensive and imposes significant overhead regarding time and costs. Self-supervised learning (SSL) partially…

Geospatial object segmentation, as a particular semantic segmentation task, always faces with larger-scale variation, larger intra-class variance of background, and foreground-background imbalance in the high spatial resolution (HSR) remote…

In the evolving landscape of multimodal language models, understanding the nuanced meanings conveyed through visual cues - such as satire, insult, or critique - remains a significant challenge. Existing evaluation benchmarks primarily focus…

The semi-supervised semantic segmentation (S4) can learn rich visual knowledge from low-cost unlabeled images. However, traditional S4 architectures all face the challenge of low-quality pseudo-labels, especially for the teacher-student…

Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already…

We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…

This paper explores the potential for performing temporal semantic segmentation in the context of agricultural robotics without temporally labelled data. We achieve this by proposing to generate virtual temporal samples from labelled still…

Sequence labeling (SL) is a fundamental research problem encompassing a variety of tasks, e.g., part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc. Though prevalent and effective in many downstream applications…

Remote sensing image plays an irreplaceable role in fields such as agriculture, water resources, military, and disaster relief. Pixel-level interpretation is a critical aspect of remote sensing image applications; however, a prevalent…

The rapid development of deep learning has driven significant progress in image semantic segmentation - a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e.,…

Accurate wetland land-cover classification is essential for environmental monitoring, biodiversity assessment, and sustainable ecosystem management. However, the scarcity of annotated data, especially for high-resolution satellite imagery,…

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of categories, requiring generalization to unseen and unlabelled objects. Using vision-language models (VLMs) to correlate local image patches with…

Due to the lack of extensive precisely-annotated multi-label data in real word, semi-supervised multi-label learning (SSMLL) has gradually gained attention. Abundant knowledge embedded in vision-language models (VLMs) pre-trained on…

In recent years, the geospatial industry has been developing at a steady pace. This growth implies the addition of satellite constellations that produce a copious supply of satellite imagery and other Remote Sensing data on a daily basis.…

What information is sufficient to learn the full richness of human scene understanding? The distributional hypothesis holds that the statistical co-occurrence of language and images captures the conceptual knowledge underlying visual…

Effective foundation modeling in remote sensing requires spatially aligned heterogeneous modalities coupled with semantically grounded supervision, yet such resources remain limited at scale. We present GeoMeld, a large-scale multimodal…

Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods frequently struggle with generalization due to incomplete and…

Vision Language Models (VLMs) have achieved impressive performance in 2D image understanding, however they are still struggling with spatial understanding which is the foundation of Embodied AI. In this paper, we propose SpatialBot for…

Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains. Despite this promise, spatial understanding and reasoning -- a fundamental component of human…

We introduce a unique semantic segmentation dataset of 6,096 high-resolution aerial images capturing indigenous and invasive grass species in Bega Valley, New South Wales, Australia, designed to address the underrepresented domain of…