AI Paper Atlas

Research map / Point clouds / Segmentation and detection

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

Qiao Wu, Jiaqi Yang, Kun Sun, Chu'ai Zhang, Yanning Zhang, Mathieu Salzmann

ICCV 2023 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 10 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 MixCycle semi-supervised training with unlabeled data to P2B at 1% labelsP2B · KITTI (1% labels)Precision: 5.0 -> 33.4Improved
add MixCycle to P2B using 10% labels versus fully supervised P2B with 100% labelsP2B · KITTISuccess: 42.4 -> 43.8Improved
MixCycle with 10% labels versus fully supervised BAT with 100% labelsBAT · KITTISuccess: 51.2 -> 46.2Hurt
add MixCycle with all labelsBAT · KITTI Car, 100% labelsSuccess: 60.5 -> 64.7Improved
add SOTMixup to the cycle tracking framework (ablation)MixCycle · KITTI 10% labelsSuccess: 38.8 -> 46.2Improved
use forward-backward cycle instead of only self cycle (ablation)MixCycle · KITTI 10% labelsSuccess: 34.9 -> 38.4Improved
combine self cycle with forward-backward cycle (ablation)MixCycle · KITTI 10% labelsSuccess: 38.4 -> 39.5Improved
add random rigid transformation without SOTMixup (ablation)MixCycle · KITTI 10% labelsSuccess: 39.5 -> 38.8Hurt
add random rigid transformation together with SOTMixup (ablation)MixCycle · KITTI 10% labelsSuccess: 44.6 -> 46.2Improved
use 3-step forward-backward cycle instead of 2 steps (ablation)MixCycle · KITTI 10% labelsSuccess: 45.8 -> 46.2Improved
apply SOTMixup to the search area only instead of also template (ablation)MixCycle · KITTI 10% labelsSuccess: 44.5 -> 46.2Improved
apply SOTMixup also in backward tracking (ablation)MixCycle · KITTI 10% labelsSuccess: 46.2 -> 44.7Hurt

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