AI Paper Atlas

Research map / Detection and segmentation / CNN features

Uncertainty-Aware Gradient Stabilization for Small Object Detection

Huixin Sun, Yanjing Li, Linlin Yang, Xianbin Cao, Baochang Zhang

ICCV 2025 · Detection and segmentation › CNN features · approach: Box regression and loss design · 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
replace L2 with classification-based localization (L_CE) (ablation)Faster R-CNN R-50 · VisDrone val (Faster R-CNN R-50, ablation)AP: 21.3 -> 22.1Improved
add interval non-uniform (IN) quantized labels (ablation)L_CE · VisDrone val (Faster R-CNN R-50, ablation)AP: 22.1 -> 22.5Improved
add uncertainty minimization loss (lambda 0.5) (ablation)L_CE+IN · VisDrone val (Faster R-CNN R-50, ablation)AP: 22.5 -> 22.9Improved
increase UM weight lambda from 0.5 to 1.0 (ablation)L_CE+IN+UM · VisDrone val (Faster R-CNN R-50, ablation)AP: 22.9 -> 22.6Hurt
add uncertainty-guided refinement (UR) module (ablation)L_CE+UM · VisDrone val (Faster R-CNN R-50, ablation)AP: 22.9 -> 24.2Improved
raise UR perturbation rho from 0.5 to 1 (ablation)UGS · VisDrone val (Faster R-CNN R-50, ablation)AP: 24.2 -> 23.2Hurt
replace L2 with Smooth-L1 loss (ablation)Faster R-CNN R-50 · VisDrone val (Faster R-CNN R-50, ablation)AP: 21.3 -> 21.5No clear effect
replace L2 with gradient clipping (ablation)Faster R-CNN R-50 · VisDrone val (Faster R-CNN R-50, ablation)AP: 21.3 -> 21.6No clear effect
replace L2 with Bayesian YOLO (ablation)Faster R-CNN R-50 · VisDrone val (Faster R-CNN R-50, ablation)AP: 21.3 -> 22.0Improved
add UGSFaster R-CNN · VisDrone valAP: 21.3 -> 24.2Improved
add UGSDINO-5scale · VisDrone valAP: 35.5 -> 38.1Improved
add UGSRotated RetinaNet · SODA-A testAP: 22.3 -> 26.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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