AI Paper Atlas

Research map / Detection and segmentation / CNN features

Slim-DETR: Real-Time Tiny Object Detection with Efficient Interaction and Gaussian Query

Tong Wu, Jiahao Zhang, Juntao Guan, Lai Rui

ECCV 2026 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 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 multi-scale Transformer encoder layer (Variant A) (ablation)RT-DETR baseline encoder · VisDrone val (B2-B4 input)AP: 30.7 -> 31.3Improved
add multi-scale Transformer encoder layer (Variant A) (ablation)RT-DETR baseline encoder · VisDrone val (B2-B4 input)latency (ms): 100 -> 166.66Hurt
add gather-and-inject mechanism (Variant B over A) (ablation)encoder with multi-scale layer · VisDrone val (B2-B4 input)AP: 31.3 -> 33.1Improved
add gather-and-inject mechanism (Variant B over A) (ablation)encoder with multi-scale layer · VisDrone val (B2-B4 input)latency (ms): 166.66 -> 28.57Improved
add FSDA foreground-token attention (Variant C over B) (ablation)EI encoder · VisDrone val (B2-B4 input)AP: 33.1 -> 33.3Improved
add FSDA foreground-token attention (Variant C over B) (ablation)EI encoder · VisDrone val (B2-B4 input)latency (ms): 28.57 -> 24.39Improved
add gather-and-inject mechanism (Variant B over A) (ablation)encoder with multi-scale layer · VisDrone val (B3-B5 input)AP: 29.1 -> 30.0Improved
add FSDA (Variant C over B) (ablation)EI encoder · VisDrone val (B3-B5 input)AP: 30.0 -> 30.3Improved
use higher-resolution B2 features instead of B3-B5 (full variant C) (ablation)EI encoder · VisDrone valAP: 30.3 -> 33.3Improved
add CBAM and gate to gathered features (ablation)EI encoder · VisDrone valfeature map qualityImproved
replace uncertainty-minimal query selection with GTG (6 layers) (ablation)Slim-DETR-R50 · VisDrone valAP: 33.3 -> 33.5Improved
reduce decoder depth from 6 to 4 layers with GTG (ablation)Slim-DETR-R50 · VisDrone valAP: 33.5 -> 33.9Improved

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