arXiv:2610.09849v1 Announce Type: new Abstract: Selecting synthetic degradations for dense prediction requires an estimate of their training utility, the generalization gain they bring under a finite...
The study investigates shortcut learning in geospatial foundation model embeddings for cross-disaster damage assessment. By holding out entire disasters during evaluation, the authors demonstrate a significant drop in mean balanced accuracy across multiple datasets, revealing that models rely on event or scene characteristics rather than transferable evidence. They further show that simple feature-level transformations, such as supervised contrastive learning or PCA, can improve generalization to unseen disasters.
Selecting synthetic degradations for dense prediction requires an estimate of their training utility, the generalization gain they bring under a finite training budget. Clean and degraded twins share...
arXiv:2609.37013v1 Announce Type: cross Abstract: Rapid assessment of building damage after natural disasters is essential to support emergency response. Earth Observation satellites can acquire rele...
SAFIRE is a large-scale benchmark for fire and smoke understanding in multimodal large language models (MLLMs), featuring 83,000 captioned images across 20 scenarios and 193,000 multiple-choice VQA questions derived from a 9.7K-image subset. The benchmark evaluates 10 dimensions of performance, from basic perception to higher-order reasoning, and employs a GPT‑5.4-assisted verification pipeline to ensure annotation quality. Experiments on ten open-source MLLMs (8B–38B) reveal an average accuracy of 61.9%, highlighting significant gaps in safety-critical reasoning, while fine-tuning vision encoders on just 7% of SAFIRE data boosts fire-scene classification accuracy from 20.1% to 64.5%. All resources are publicly available at https://risys-lab.github.io/SAFIRE/.
arXiv:2609.13791v1 Announce Type: new Abstract: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom...
arXiv:2601.18493v2 Announce Type: replace Abstract: Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-ce...
Cache-based test-time adaptation improves CLIP predictions by storing and retrieving examples from the target stream while keeping the model frozen. However, existing methods largely treat the feature...
arXiv:2609.31170v1 Announce Type: new Abstract: Task-driven image restoration aims to improve both image quality and downstream task performance. However, existing methods predominantly focus on sing...
Loop‑Mamba is a lightweight, loop‑based state‑space framework designed for restoring old photographs that suffer from multiple degradations such as scratches, cracks, fading, blur, noise, and missing regions. It models restoration as progressive state evolution, using a Semantic‑Guided Degradation Estimator to predict local degradation maps and global scores, and a Shared Structural Memory Mamba to maintain a persistent restoration state across iterations. The method employs first‑order state recursion and a multi‑directional scanning strategy to reduce gradient dilution and computational overhead, and introduces the Old Photo Damage Recovery Score (ODRS) to evaluate both degradation recovery and structural reconstruction, achieving superior performance on the SynOld benchmark.
arXiv:2607. 22705v1 Announce Type: cross Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations.
DisasterInsight is a building‑centric benchmark designed to evaluate vision‑language models (VLMs) for disaster response. Built on the xBD satellite dataset, it adds OpenStreetMap‑derived functional labels to 134,108 building instances and offers 15 task types, including instance assessment, scene counting, multi‑instance reasoning, and structured report generation. Experiments show that VLMs excel at visible damage detection but struggle with building function, multi‑instance reasoning, counting, and grounded reporting, and instruction tuning only partially mitigates these gaps.