mlsanityData to 14 Oct 2026

AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives

arXiv 2506.03709 ↗First posted 4 Jun 2025cs.CVcited by 0

On the map: World models → World models for navigation

Abstract (arXiv)

Open-vocabulary semantic segmentation (OVSS) involves assigning labels to each pixel in an image based on textual descriptions, leveraging world models like CLIP. However, they encounter significant challenges in cross-domain generalization, hindering their practical efficacy in real-world applications. Embodied AI systems are transforming autonomous navigation for ground vehicles and drones by enhancing their perception abilities, and in this study, we present AetherVision-Bench, a benchmark for multi-angle segmentation across aerial, and ground perspectives, which facilitates an extensive evaluation of performance across different viewing angles and sensor modalities. We assess state-of-the-art OVSS models on the proposed benchmark and investigate the key factors that impact the performance of zero-shot transfer models. Our work pioneers the creation of a robustness benchmark, offering valuable insights and establishing a foundation for future research.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for navigation, one of 11 directions in World models. Builds on 25 of its 34 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

25 of 34 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  3. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  4. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  5. 2021Florence: A New Foundation Model for Computer Visioncited by 804
  6. 2021Robust fine-tuning of zero-shot modelscited by 797
  7. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  8. 2021Extract Free Dense Labels from CLIPcited by 583
  9. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 565
  10. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 473
  11. 2023Side Adapter Network for Open-Vocabulary Semantic Segmentationcited by 300
  12. 2022Generalized Decoding for Pixel, Image, and Languagecited by 294
13 more
  1. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  2. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 219
  3. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 201
  4. 2023DePT: Decoupled Prompt Tuningcited by 58
  5. 2023What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentationcited by 24
  6. 2024Caltech Aerial RGB-Thermal Dataset in the Wildcited by 19
  7. 2024LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomiescited by 12
  8. 2023MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbationcited by 11
  9. 2022Fully Complex-valued Fully Convolutional Multi-feature Fusion Network (FC2MFN) for Building Segmentation of InSAR imagescited by 4
  10. 2024Syn2Real Domain Generalization for Underwater Mine-like Object Detection Using Side-Scan Sonarcited by 4
  11. 2025SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systemscited by 4
  12. 2022An Efficient Approach with Dynamic Multi-Swarm of UAVs for Forest Firefightingcited by 2
  13. 2024A Resource-Efficient Decentralized Sequential Planner for Spatiotemporal Wildfire Mitigationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Do Open-Vocabulary Detectors Transfer to Aerial Imagery? A Comparative Evaluation
  2. 2025RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models
  3. 2026GeoRefer-Bench: A Benchmark from Referring Pixels to Verifiable Geospatial Reasoning
  4. 2026Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation
  5. 2026DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models
  6. 2024Open-RGBT: Open-vocabulary RGB-T Zero-shot Semantic Segmentation in Open-world Environments
  7. 2026Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
  8. 2025RGB-Th-Bench: A Dense benchmark for Visual-Thermal Understanding of Vision Language Models