AI Paper Atlas

Research map / Detection and segmentation / CNN features

ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer

Wenxi Li, Jingchen Huang, Chenyang Lyu, Moran Liu, Haozhe Lin, Guiguang Ding, Yuchen Guo

CVPR 2026 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 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
replace fixed-ratio SparseFormer backbone with ElasticFormerDINO · PANDAAP50: 0.780 -> 0.806Improved
replace SparseFormer with ElasticFormerDINO · PANDAoverall GFLOPs: 75.71 -> 13.13Improved
replace SparseFormer with ElasticFormerDynamic-Head · PANDAAP50: 0.771 -> 0.782Improved
replace SparseFormer with ElasticFormerModified-DINO · PASCAL VOC 2007 (WSOD)mAP: 50.3 -> 50.9Improved
use 3-phase training instead of 1-phase (ablation)ElasticFormer (pseudo-GT) · PANDAAP50: 0.784 -> 0.806Improved
supervise with pseudo-GT instead of GT (ablation)ElasticFormer (3-phase) · PANDAAP50: 0.798 -> 0.806Improved
increase gamma from 0.1 to 0.3 (ablation)ElasticFormer · PANDAAP50 / GFLOPs: 0.806 -> 0.795 AP50; 13.13 -> 10.28 GFLOPsMixed
lower alpha from 1.0 to 0.8 (ablation)ElasticFormer · PANDAAP50: 0.802 -> 0.806Improved
lower alpha from 0.8 to 0.6 (ablation)ElasticFormer · PANDAAP50: 0.806 -> 0.799Hurt
use variance scoring instead of small learned objectness (ablation)ElasticFormer · PANDAAP50 / latency: 0.803 -> 0.806 AP50; 1.213 -> 0.397 msMixed
use variance scoring instead of gradient density (ablation)ElasticFormer · PANDAAP50: 0.798 -> 0.806Improved
use ElasticNet (conv) instead of ResNet-50 backboneDINO · PANDAAP50 / GFLOPs: 0.542 -> 0.754 AP50; 124.24 -> 16.54 GFLOPsImproved

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