AI Paper Atlas

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

MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos

Yihong Sun, Bharath Hariharan

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 1 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 Moving2Mobile self-training stage (ablation)MOD-UV‡ · Waymo Open valBox AR / AP: AR 12.6 -> 17.5; AP 7.0 -> 10.9Improved
add Large2Small small-object detector (ablation)MOD-UV‡ · Waymo Open valBox AR_S / AP_S: AR_S reduces nearly 4x and AP_S 3x when removed; AR 12.5 -> 17.5Improved
add final self-training round on aggregated proposals (ablation)MOD-UV‡ · Waymo Open valBox AR: +8.1 vs large-only, +4.1 vs small-only detectorImproved
cluster pseudo-3D points from monocular depth instead of 2D contours for pseudo-labels (ablation)motion-segmentation pseudo-labels · Waymo trainMoving Mask AR_L: +9.4 Moving AR_L, +2.5 Moving ARImproved
train Moving2Mobile beyond 3 epochs (ablation)MOD-UV‡ · Waymo train pseudo-labelsMask AR (all): 5.3 (3 epochs) -> 4.3 (5 epochs) -> 4.1 (20 epochs)Hurt
Moving2Mobile alone for small objects (ablation)MOD-UV‡ · Waymo train pseudo-labelsAR_S: 0.0 -> 0.0No clear effect
add Large2Small to CutLER (no motion cues)CutLER · Waymo Open valBox AR: 11.7 -> 15.0Improved
replace NMS with proposed mask aggregation of large and small detector outputs (ablation)MOD-UV · Waymo Open valAR0.5 / AP50: +1.8 AR0.5, +1.5 AP50Improved
use motion-based pseudo-labels instead of image-feature-only (CutLER^L2S)MOD-UV · Waymo Open valBox AP: 4.3 -> 12.6Improved
train HASSOD only on Waymo instead of COCOHASSOD · Waymo Open valBox AR: 12.7 -> 8.3Hurt
ImageNet-initialized backbone instead of Waymo-initializedMOD-UV · nuScenes zero-shotBox AR: 17.3 -> 21.9Improved
apply Waymo-trained MOD-UV to COCO (domain shift)MOD-UV · COCO val2017 ground vehiclesBox AR: 26.6 vs HASSOD 27.9Mixed

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