AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones

Anurag Ghosh, Shen Zheng, Robert Tamburo, Khiem Vuong, Juan Alvarez-Padilla, Hailiang Zhu, Michael Cardei, Nicholas Dunn, Christoph Mertz, Srinivasa G. Narasimhan

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Feature calibration for unseen-class detection · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune Mask DINO on ROADWork instead of open-vocabulary pretrainedMask DINO · ROADWork work zone object segmentationAP: +32.2 APImproved
add SAM2 video label propagation (ablation)Mask DINO · ROADWork work zone object segmentationAP: 36.4 -> 39.0Improved
use manual masks instead of SAM pseudo masks (ablation)Mask R-CNN · ROADWork pseudo-mask supervisionAP: +5.2 APImproved
add 5 or 10 extra points to box prompts for SAM (ablation)SAM pseudo masks · ROADWork pseudo-mask supervisionAP: 24.7 -> 25.8Improved
use SAM2 instead of SAM for pseudo masks (ablation)pseudo-mask supervision · ROADWork pseudo-mask supervisionAP: 24.7 -> 26.4No clear effect
add copy-paste augmentation (ablation)Mask R-CNN · ROADWork fine-grained sign segmentationAP: 17.6 -> 25.0Improved
add video label propagation (ablation)Mask DINO · ROADWork fine-grained sign segmentationAP: 30.0 -> 32.8Improved
add crop-rescaling with detector before Glass (ablation)Glass · ROADWork sign text reading (all signs)1-NED: 65.4 -> 79.6Improved
increase crop scale from 1x to 3x (ablation)Glass · ROADWork sign text reading (all signs)Word Acc.: 56.3 -> 59.6Improved
add crop-rescaling for small signs (ablation)Glass · ROADWork sign text reading (small signs)Word Acc.: 13.2 -> 32.3Improved
fine-tune LLaVA-1.5-7B on ROADWorkLLaVA-1.5-7B · ROADWork scene descriptionSPICE: 9.9 -> 42.7Improved
add predicted object context to prompt (ablation)LLaVA-1.5-7B · ROADWork scene descriptionSPICE: 42.7 -> 46.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy