CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Prediction
Long-tail autonomous driving failures are often framed as rare-object recognition errors. We argue that this view is incomplete: the decision-critical question is not only whether a model recognizes an unusual object, but whether it infers how that object changes the ego vehicle's feasible high-level actions. We formalize this problem as decision-level driving affordance prediction, where a model maps a front-view image, ego-motion history, and navigation command to a structured longitudinal--lateral meta-action. To evaluate this capability, we introduce CoLT-Drive, a 3,536-sample counterfactual long-tail benchmark that inserts rare objects into otherwise fixed driving scenes and measures...
| Authors | Zhengxu Tang, Guofeng Cui, Ziyu Gong et al. |
|---|---|
| Primary category | cs.CV |
| Published | 31 August 2026 |
| Last updated at source | 31 August 2026 |
Connected in the knowledge graph
- tangzx2024/CoLT-DriveDataset · cited by
Models and datasets referencing this paper
- tangzx2024/CoLT-DriveDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.