AI Paper Atlas

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

MonoTTA: Fully Test-Time Adaptation for Monocular 3D Object Detection

Hongbin Lin, Yifan Zhang, Shuaicheng Niu, Shuguang Cui, Zhen Li

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 16 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 reliability-driven adaptation loss L_AO (ablation)MonoGround · KITTI-C level 1 (avg)mean AP3D|R40: 5.17 -> 14.40Improved
add negative regularization L_Nreg (ablation)MonoGround · KITTI-C level 1 (avg)mean AP3D|R40: 5.17 -> 12.15Improved
combine L_AO with L_Nreg (ablation)MonoGround · KITTI-C level 1 (avg)mean AP3D|R40: 14.40 -> 16.79Improved
combine L_AO with L_Nreg at severity level 2 (ablation)MonoGround · KITTI-C level 2 (avg)mean AP3D|R40: 10.96 -> 12.85Improved
use MonoTTA instead of TENT on MonoGround carsMonoGround · KITTI-C level 1 Carmean AP3D|R40: 27.54 -> 32.64Improved
use MonoTTA instead of EATA on MonoGround carsMonoGround · KITTI-C level 1 Carmean AP3D|R40: 25.28 -> 32.64Improved
apply any TTA method at higher severity (level 2)TTA methods on KITTI-C · KITTI-C level 2mean AP3D|R40Mixed
add MonoTTA to an instance-level (batch size 1) detectorMonoNeRD · KITTI-C level 1mean AP3D|R40: 9.36 -> 17.38Improved
use MonoTTA instead of TENT on MonoNeRD cyclistsMonoNeRD · KITTI-C level 1 Cyclistmean AP3D|R40: 4.75 -> 4.35Hurt
use entropy minimization on all detections (TENT) in the real N->D taskTENT · nuScenes Night to DaytimemAPHurt

Later papers that compared with this method

2 later accepted papers report MonoTTA as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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