WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models
Carnegie Mellon University（卡内基梅隆大学）；Symbiosis International University（共生国际大学）；Symbiosis Centre for Applied AI（共生应用人工智能中心）；Symbiosis Institute of Technology（共生技术学院）
Aboli Marathe, Deva Ramanan, Rahee Walambe, Ketan Kotecha
备注：
Accepted in Vision Datasets Understanding at CVPR 2023
The open road poses many challenges to autonomous perception, including poor visibility from extreme weather conditions. Models trained on good-weather datasets frequently fail at detection in these out-of-distribution settings. To aid adversarial robustness in perception, we introduce WEDGE (WEather images by DALL-E GEneration): a synthetic dataset generated with a vision-language generative model via prompting. WEDGE consists of 3360 images in 16 extreme weather conditions manually annotated with 16513 bounding boxes, supporting research in the tasks of weather classification and 2D object detection. We have analyzed WEDGE from research standpoints, verifying its effectiveness for extreme-weather autonomous perception. We establish baseline performance for classification and detection with 53.87% test accuracy and 45.41 mAP. Most importantly, WEDGE can be used to fine-tune state-of-the-art detectors, improving SOTA performance on real-world weather benchmarks (such as DAWN) by 4.48 AP for well-generated classes like trucks. WEDGE has been collected under OpenAI's terms of use and is released for public use under the CC BY-NC-SA 4.0 license. The repository for this work and dataset is available at https://infernolia.github.io/WEDGE.
Pan-Arctic Permafrost Landform and Human-built Infrastructure Feature Detection with Vision Transformers and Location Embeddings
University of Connecticut（康涅狄格大学）；Google（谷歌）；Woodwell Climate Research Center（伍德韦尔气候研究中心）；National Center for Supercomputing Applications, University of Illinois（伊利诺伊大学国家超级计算应用中心）
