The paper proposes a method called Restrict, Don't Retrain that enhances zero-shot aerial segmentation by using inference-time guidance from a vision‑language model (VLM). It combines a frozen foundation model that labels every pixel with two VLM queries: one to select relevant classes and another to locate small objects missed by the base model. Experiments on four aerial datasets show consistent performance gains at each stage where the base model is competent.
arXiv:2609.38603v1 Announce Type: new Abstract: While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability...
arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image...
arXiv:2610.33056v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) have revolutionized general visual perception, existing methods suffer from severe hallucination in th...
IVSGround introduces a lightweight view selector that learns to choose the most informative camera views for vision‑language model (VLM) based 3D visual grounding, replacing heuristic view selection. The selector is trained via a two‑stage rejection sampling process that uses feedback from a reasoning VLM to generate supervision signals. Experiments on ScanRefer and NR3D demonstrate that IVSGround consistently improves grounding accuracy over existing zero‑shot pipelines, underscoring the importance of selecting where to look for effective 3D visual grounding.
arXiv:2603.16932v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational ef...
arXiv:2607. 02718v1 Announce Type: cross Abstract: Recent advances in large-scale image generative models enable photorealistic scene synthesis with controllable attributes.
Vision-Language Models (VLMs) are promising for construction-site monitoring, and recent construction-tailored VLMs have primarily adapted pretrained VLMs through direct QA-style fine-tuning from a single global image. We argue that this direct paradigm remains limited for in-the-wild deployment in terms of operational range, reliability under reduced-resolution inputs, and inference efficiency.
arXiv:2605. 20306v2 Announce Type: replace-cross Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous research-and-engineering by LLM-driven agents on a single professionally annotated UAV corpus.
The paper investigates using Vision Language Models (VLMs) to accelerate verification and validation (V&V) of classification models by automatically detecting systematic errors. It introduces a VLM-based error slice detection (ESD) method that groups and labels errors, demonstrating its ability to identify perturbations in a non-military dataset and to cluster images by surroundings in a military context. The study highlights challenges such as underrepresentation of defence data in VLM training and limited contextual diversity, and suggests that while fully automated V&V is not yet feasible, VLMs could speed up the process in the future.
arXiv:2609.37481v1 Announce Type: new Abstract: Large-scale pervasive sensing increasingly relies on high-resolution satellite imagery, yet task-specific onboard vision is constrained by costly annot...
arXiv:2609.22897v1 Announce Type: cross Abstract: Large vision-language models (VLMs) enable recognition beyond a fixed class set, but their computational demands prevent them from running on many ed...
arXiv:2606. 16996v1 Announce Type: cross Abstract: Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabulary semantic segmentation (OVSS) is inefficient: full-resolution decoding is typically run over the entire dataset vocabulary, whereas each image contains only a small active subset of classes.