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

arXiv: https://arxiv.org/abs/2303.09219 · HTML: https://mlsanity.com/paper/2303.09219/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 27 of 27)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [PointMixup: Augmentation for Point Clouds](https://mlsanity.com/paper/2008.06374/) (2020)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds](https://mlsanity.com/paper/2005.13888/) (2020)
- [Leveraging Shape Completion for 3D Siamese Tracking](https://mlsanity.com/paper/1903.01784/) (2019)
- [Unsupervised Deep Tracking](https://mlsanity.com/paper/1904.01828/) (2019)
- [PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds](https://mlsanity.com/paper/2208.00223/) (2022)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2108.04728/) (2021)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2108.06455/) (2021)
- [Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2203.01730/) (2022)
- [3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds](https://mlsanity.com/paper/2111.04426/) (2021)
- [CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09778/) (2022)
- [3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud](https://mlsanity.com/paper/2108.05630/) (2021)
- [3D Siamese Transformer Network for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2207.11995/) (2022)
- [Unsupervised Deep Representation Learning for Real-Time Tracking](https://mlsanity.com/paper/2007.11984/) (2020)
- [Learning to Track Objects from Unlabeled Videos](https://mlsanity.com/paper/2108.12711/) (2021)
- [Efficient Bird Eye View Proposals for 3D Siamese Tracking](https://mlsanity.com/paper/1903.10168/) (2019)
- [SageMix: Saliency-Guided Mixup for Point Clouds](https://mlsanity.com/paper/2210.06944/) (2022)
- [Self-supervised Object Tracking with Cycle-consistent Siamese Networks](https://mlsanity.com/paper/2008.00637/) (2020)
- [Importance is in your attention: agent importance prediction for autonomous driving](https://mlsanity.com/paper/2204.09121/) (2022)
- [What Can be Seen is What You Get: Structure Aware Point Cloud Augmentation](https://mlsanity.com/paper/2206.09664/) (2022)

## Built on by (most cited first, 3 of 3)

- [QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration](https://mlsanity.com/paper/2603.08030/) (2026)
- [3D Single-object Tracking in Point Clouds with High Temporal Variation](https://mlsanity.com/paper/2408.02049/) (2024)
- [FARTrack: Fast Autoregressive Visual Tracking with High Performance](https://mlsanity.com/paper/2602.03214/) (2026)

## Abstract (arXiv)

3D single object tracking (SOT) is an indispensable part of automated driving. Existing approaches rely heavily on large, densely labeled datasets. However, annotating point clouds is both costly and time-consuming. Inspired by the great success of cycle tracking in unsupervised 2D SOT, we introduce the first semi-supervised approach to 3D SOT. Specifically, we introduce two cycle-consistency strategies for supervision: 1) Self tracking cycles, which leverage labels to help the model converge better in the early stages of training; 2) forward-backward cycles, which strengthen the tracker's robustness to motion variations and the template noise caused by the template update strategy. Furthermore, we propose a data augmentation strategy named SOTMixup to improve the tracker's robustness to point cloud diversity. SOTMixup generates training samples by sampling points in two point clouds with a mixing rate and assigns a reasonable loss weight for training according to the mixing rate. The resulting MixCycle approach generalizes to appearance matching-based trackers. On the KITTI benchmark, based on the P2B tracker, MixCycle trained with 10% labels outperforms P2B trained with 100% labels, and achieves a 28.4% precision improvement when using 1% labels. Our code will be released at urlhttps://github.com/Mumuqiao/MixCycle.