The First Workshop onOut-of-Label Hazards in Autonomous Driving

WACV Conference with challenging benchmark" COOOL"

Feb.28 - Mar.4 2025 in Tucson, Arizona

In recent years, the field of autonomous vehicles has rapidly expanded, driven by advancements in AI, machine learning, and sensor technologies that promise to enhance safety, reduce traffic accidents, and improve mobility. Avoiding hazards is essential from the safety perspective for a robust system, and there is room for further improvement. A robust autonomous vehicle system should be able to identify and appropriately respond to unexpected or previously unseen hazards to avoid accidents. In this workshop, we encourage researchers to address the limitations of current approaches for avoiding hazards on the road by proposing new algorithms and systems that advance the field, in particular with solutions inspired by novelty-adjacent areas such as Anomaly Detection, Open-Set Recognition, Open Vocabulary, and Domain Adaptation. 

Topics

The list of topics includes but is not limited to the following:

• Detecting, recognizing, predicting, and avoiding out-of-label hazards in autonomous driving.

• Detecting, recognizing, predicting activity understanding in autonomous driving 

• Handling low-resolution hazards.

• New datasets and metrics for autonomous driving.

• Vision systems for autonomous driving.

• Vision-language models for autonomous driving.

• Explainable AI (XAI) in autonomous driving.

• 
  

Challenge Of Out-Of-Label (COOOL) in Autonomous Driving:

We have constructed a novel benchmark, Challenge Of Out-Of-Label (COOOL) in Autonomous Driving. This benchmark features high-resolution videos from real-world driving scenarios. COOOL is an evaluation benchmark focused exclusively on diverse roadway hazards, including exotic animals like kangaroos and wild boars, inanimate and hard-to-predict hazards like plastic bags and smoke, and standard hazards like cars and pedestrians. Using vision information to detect out-of-label hazards on roadways is an often overlooked problem in autonomous driving research; our benchmark highlights this issue exclusively. It includes detailed labels for each object in every frame, enhancing research capabilities. A unique aspect of our benchmark is the “Tag” information for each frame, which provides insights into the car's movements and the driver's decisions. Undergraduate students at the University of Colorado Colorado Springs (UCCS) and local high school students have annotated the benchmark using a professional computer vision annotation platform under the guidance of expert graduate students and professors.

Important Dates

Workshop paper submission deadline: December 23rd 

Workshop Reviews deadline: January 6th 

Workshop paper acceptance notification: January 8th

Workshop paper camera ready: January 10th