AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges

Jian Ding, Nan Xue, Gui-Song Xia, Xiang Bai, Wen Tao Yang, Michael Ying Yang, Serge Belongie, Jiebo Luo, Mihai P. Datcu, Marcello Pelillo, Liangpei Zhang

TPAMI 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 761 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 high patch overlap (512 instead of 200) (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v1.5OBB mAP: 65.03 -> 67.57Improved
add multi-scale training (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v1.5OBB mAP: 67.57 -> 69.44Improved
add multi-scale testing (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v1.5OBB mAP: 69.44 -> 73.62Improved
add rotation training (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v1.5OBB mAP: 73.62 -> 76.43Improved
add rotation testing (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v1.5OBB mAP: 76.43 -> 77.60Improved
replace RoI Align with RoI Transformer (ablation)Faster R-CNN OBB · DOTA-v2.0 test-devOBB mAP: 47.31 -> 52.81Improved
replace RoI Align with deformable RoI pooling (Dpool) (ablation)Faster R-CNN OBB · DOTA-v2.0 test-devOBB mAP: 47.31 -> 48.77Improved
use mask head instead of OBB head (Mask R-CNN vs Faster R-CNN H-OBB)Faster R-CNN · DOTA-v2.0 test-devOBB mAP: +0.57 points; 4 fps slowerImproved
increase proposals from 1,000 to 10,000 (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v2.0 test-devOBB mAP: 51.72 -> 53.92; speed 14.4 -> 5.7 fpsImproved
increase proposals from 1,000 to 10,000 (ablation)Faster R-CNN OBB · DOTA-v2.0 test-devOBB mAP: 47.10 -> 48.49; speed 15.8 -> 7.8 fpsImproved
exclude small instances (area <= 50 and max(w,h) <= 10) (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v2.0HBB mAP: 51.08 / 51.35 / 50.71 across thresholdsNo clear effect
filter more small instances (area <= 80, max(w,h) <= 12 vs <= 10) (ablation)Faster R-CNN OBB + RoI Transformer · DOTA-v2.0HBB mAP: 51.35 -> 50.71Hurt

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