A foundation-guided auto-annotation pipeline that enhances standard detectors without architectural changes and demonstrates that standard detectors can achieve environmental resilience without the need for extensive manual annotation or architectural modifications is proposed.
Abstract
Standard deployment-ready object detectors for autonomous vehicles degrade in adverse weather and lighting conditions without being trained on extensive domain-specific data. While large-scale vision foundation models offer robust zero-shot generalization, their high computational cost makes them impractical for real-time deployment. To bridge this gap, we propose a foundation-guided auto-annotation pipeline that enhances standard detectors without architectural changes. We first benchmark three distinct models, YOLOv8, Co-DETR, and SAM3, on our custom real-world driving dataset spanning 25 unique operational scenarios across various route, weather, and lighting conditions. Based on our analysis, SAM3 demonstrates superior accuracy and resilience across all scenarios. Thus, we deploy it as an offline auto-annotator to generate pseudo-labels on the unannotated subset of our dataset. Fine-tuning the baseline YOLOv8 on these annotations yields a 16.04% higher overall mean Average Precision (mAP) and improves cross-environmental stability compared to the baseline model, highlighted by a 32.73% and 28.65% mAP increase in Residential Direct Sunlight and Highway Fog, respectively. These results demonstrate that standard detectors can achieve environmental resilience without the need for extensive manual annotation or architectural modifications.
A structured evaluation protocol is proposed that assesses the deployment readiness of LiDAR semantic segmentation models along three complementary dimensions: coarse-label evaluation aligned with autonomous driving safety priorities, revealing how label granularity affects different methods; robustness under eight typ...
Samir Abou Haidar, Alexandre Chariot, Mehdi Darouich et al.· 0 citations
Reliable drone detection under real-world deployment conditions requires training data that spans the full operational design domain, including adverse weather and seasonal appearance variation. However, acquiring and annotating such data at scale remains highly resource-intensive, as adverse-weather conditions are inh...
T. Lenhard, Andreas Weinmann, Tobias Koch· 0 citations
This paper adapts set difference captioning to autonomous driving by focusing on object-centric patches derived from object detection, which simplifies aggregation and enables attribution of differences to specific object instances or categories and introduces a new benchmark, AD-Diff Bench.
Julian Truetsch, Felix Hauser, Christoph Stiller et al.· 0 citations
Experimental results show that ROSE achieves competitive detection accuracy while providing improved robustness and cross-modal consistency across adverse weather scenarios, demonstrating strong generalization potential for roadside multi-modal perception under challenging environmental conditions.
Guo-Yu Zhang, Peng Hang, Xin Xia et al.· Communications in Transporta...· 0 citations
ST-MaskContrast incorporates a decoupled space-time token masking strategy coupled with a multi-scale cross-attention temporal decoder that enforces invariant representations between clean and corrupted sequential frames via contrastive patch-level loss, providing unprecedented perceptual resilience for safety-critical...
Rashed Karim Bipul· International Journal of App...· 0 citations
Wildlife-vehicle collisions remain a significant road safety concern, particularly during nighttime and low-visibility conditions when RGB-based perception systems are often unreliable. Thermal imaging offers a promising alternative for detecting animals under poor illumination. However, the limited availability of ann...
James Momoh, Khandaker Mamun Ahmed· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.