AI Paper Atlas

Research map / Detection and segmentation / CNN features

DM-EFS: Dynamically Multiplexed Expanded Features Set Form for Robust and Efficient Small Object Detection

Aashish Sharma

ICCV 2025 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 2 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 EFS form (use higher-resolution shallow backbone features) (ablation)YOLOv7 · VisDrone val (640x640)AP50: 47.81 -> 52.01Improved
add EFS form (ablation)YOLOv7 · VisDrone val (640x640)fps: 39.71 -> 32.14Hurt
add dynamic feature multiplexing (DFM) to EFS form (ablation)YOLOv7 + EFS · VisDrone val (640x640)fps: 32.14 -> 38.24Improved
add dynamic feature multiplexing (DFM) to EFS form (ablation)YOLOv7 + EFS · VisDrone val (640x640)AP50: 52.01 -> 51.80No clear effect
swap in size-features codebook learned on DarkFace (ablation)DM-EFS · VisDrone val (640x640)AP: 29.71 -> 29.13No clear effect
swap in size-features codebook learned on VisDrone (ablation)DM-EFS · DarkFace val (640x640)AP: 29.30 -> 28.95No clear effect
raise lambda_szp to 0.04 from <=0.02 (ablation)DM-EFS · VisDrone val (640x640)AP50Improved
raise lambda_szp to >=0.06 (ablation)DM-EFS · VisDrone val (640x640)AP50Hurt
use DM-EFS instead of ESOD with same YOLOv7 baseYOLOv7 · VisDrone val (640x640)AP: 27.16 -> 29.71Improved
use DM-EFS instead of ESOD with RetinaNet baseRetinaNet · VisDrone val (640x640)AP: 08.91 -> 09.11Improved
use DM-EFS instead of ESOD with YOLOv5 baseYOLOv5 · VisDrone val (640x640)AP: 23.61 -> 25.14Improved
add DM-EFS to YOLOv7 on SODA-DYOLOv7 · SODA-D test (640x640)AP: 30.52 -> 34.91Improved

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