AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

DiverseAD: A Large-Scale Driving Dataset with Diverse Atmospheric Conditions

Haoyu Wang, Baorui Ma, Donglin Di, Suhang Xuan, Hao Li, Shiliang Zhang

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 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
add driving-intent anchored loss (ablation)Ours · DiverseADAvg. L2 (m): 1.39 -> 1.24Improved
use direction-based intent similarity instead of ADE (ablation)Ours · DiverseADAvg. L2 (m): 1.38 -> 1.24Improved
add scene-structure anchored loss (ablation)Ours · DiverseADAvg. L2 (m): 1.42 -> 1.24Improved
use DINOv3 features instead of Gram-matrix similarity (ablation)Ours · DiverseADAvg. L2 (m): 1.35 -> 1.24Improved
use soft-weighted KL instead of contrastive loss on structure (ablation)Ours · DiverseADAvg. L2 (m): 1.33 -> 1.24Improved
use soft-weighted KL instead of contrastive loss on intent (ablation)Ours · DiverseADAvg. L2 (m): 1.38 -> 1.24Improved
use specialized scene structure expert instead of CLIP (ablation)Ours · DiverseADAvg. L2 (m): 1.37 -> 1.24Improved
use specialized scene structure expert instead of DINOv2 (ablation)Ours · DiverseADAvg. L2 (m): 1.29 -> 1.24Improved
fine-tune on DiverseADUniAD · DiverseADAvg. L2 (m): 31.17 -> 2.11Improved
fine-tune on DiverseADFSDrive · DiverseADAvg. L2 (m): 25.50 -> 1.44Improved
use atmospheric-invariant model instead of fine-tuned FSDriveOurs · DiverseADAvg. L2 (m): 1.44 -> 1.24Improved
use atmospheric-invariant model instead of OmniDriveOurs · nuScenesAvg. L2 (m): 0.40 -> 0.39No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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